Transformer Mechanisms Mimic Frontostriatal Gating Operations When Trained on Human Working Memory Tasks

Models based on the Transformer neural network architecture have seen success on a wide variety of tasks that appear to require complex "cognitive branching" -- or the ability to maintain pursuit of one goal while accomplishing others. In cognitive neuroscience, success on such tasks is thought to rely on sophisticated frontostriatal mechanisms for selective \textit{gating}, which enable role-addressable updating -- and later readout -- of information to and from distinct "addresses" of memory, in the form of clusters of neurons. However, Transformer models have no such mechanisms intentionally built-in. It is thus an open question how Transformers solve such tasks, and whether the mechanisms that emerge to help them to do so bear any resemblance to the gating mechanisms in the human brain. In this work, we analyze the mechanisms that emerge within a vanilla attention-only Transformer trained on a simple sequence modeling task inspired by a task explicitly designed to study working memory gating in computational cognitive neuroscience. We find that, as a result of training, the self-attention mechanism within the Transformer specializes in a way that mirrors the input and output gating mechanisms which were explicitly incorporated into earlier, more biologically-inspired architectures. These results suggest opportunities for future research on computational similarities between modern AI architectures and models of the human brain.

Human Curriculum Effects Emerge with In-Context Learning in Neural Networks

Human learning is sensitive to rule-like structure and the curriculum of examples used for training. In tasks governed by succinct rules, learning is more robust when related examples are blocked across trials, but in the absence of such rules, interleaving is more effective. To date, no neural model has simultaneously captured these seemingly contradictory effects. Here we show that this same tradeoff spontaneously emerges with "in-context learning" (ICL) both in neural networks trained with metalearning and in large language models (LLMs). ICL is the ability to learn new tasks "in context" - without weight changes - via an inner-loop algorithm implemented in activation dynamics. Experiments with pretrained LLMs and metalearning transformers show that ICL exhibits the blocking advantage demonstrated in humans on a task involving rule-like structure, and conversely, that concurrent in-weight learning reproduces the interleaving advantage observed in humans on tasks lacking such structure.

Uncovering Intermediate Variables in Transformers using Circuit Probing

Neural network models have achieved high performance on a wide variety of complex tasks, but the algorithms that they implement are notoriously difficult to interpret. In order to understand these algorithms, it is often necessary to hypothesize intermediate variables involved in the network's computation. For example, does a language model depend on particular syntactic properties when generating a sentence? However, existing analysis tools make it difficult to test hypotheses of this type. We propose a new analysis technique -- circuit probing -- that automatically uncovers low-level circuits that compute hypothesized intermediate variables. This enables causal analysis through targeted ablation at the level of model parameters. We apply this method to models trained on simple arithmetic tasks, demonstrating its effectiveness at (1) deciphering the algorithms that models have learned, (2) revealing modular structure within a model, and (3) tracking the development of circuits over training. We compare circuit probing to other methods across these three experiments, and find it on par or more effective than existing analysis methods. Finally, we demonstrate circuit probing on a real-world use case, uncovering circuits that are responsible for subject-verb agreement and reflexive anaphora in GPT2-Small and Medium.

Analyzing Modular Approaches for Visual Question Decomposition

Modular neural networks without additional training have recently been shown to surpass end-to-end neural networks on challenging vision-language tasks. The latest such methods simultaneously introduce LLM-based code generation to build programs and a number of skill-specific, task-oriented modules to execute them. In this paper, we focus on ViperGPT and ask where its additional performance comes from and how much is due to the (state-of-art, end-to-end) BLIP-2 model it subsumes vs. additional symbolic components. To do so, we conduct a controlled study (comparing end-to-end, modular, and prompting-based methods across several VQA benchmarks). We find that ViperGPT's reported gains over BLIP-2 can be attributed to its selection of task-specific modules, and when we run ViperGPT using a more task-agnostic selection of modules, these gains go away. Additionally, ViperGPT retains much of its performance if we make prominent alterations to its selection of modules: e.g. removing or retaining only BLIP-2. Finally, we compare ViperGPT against a prompting-based decomposition strategy and find that, on some benchmarks, modular approaches significantly benefit by representing subtasks with natural language, instead of code.

Emergence of Abstract State Representations in Embodied Sequence Modeling

Decision making via sequence modeling aims to mimic the success of language models, where actions taken by an embodied agent are modeled as tokens to predict. Despite their promising performance, it remains unclear if embodied sequence modeling leads to the emergence of internal representations that represent the environmental state information. A model that lacks abstract state representations would be liable to make decisions based on surface statistics which fail to generalize. We take the BabyAI environment, a grid world in which language-conditioned navigation tasks are performed, and build a sequence modeling Transformer, which takes a language instruction, a sequence of actions, and environmental observations as its inputs. In order to investigate the emergence of abstract state representations, we design a "blindfolded" navigation task, where only the initial environmental layout, the language instruction, and the action sequence to complete the task are available for training. Our probing results show that intermediate environmental layouts can be reasonably reconstructed from the internal activations of a trained model, and that language instructions play a role in the reconstruction accuracy. Our results suggest that many key features of state representations can emerge via embodied sequence modeling, supporting an optimistic outlook for applications of sequence modeling objectives to more complex embodied decision-making domains.

Characterizing Mechanisms for Factual Recall in Language Models

Language Models (LMs) often must integrate facts they memorized in pretraining with new information that appears in a given context. These two sources can disagree, causing competition within the model, and it is unclear how an LM will resolve the conflict. On a dataset that queries for knowledge of world capitals, we investigate both distributional and mechanistic determinants of LM behavior in such situations. Specifically, we measure the proportion of the time an LM will use a counterfactual prefix (e.g., "The capital of Poland is London") to overwrite what it learned in pretraining ("Warsaw"). On Pythia and GPT2, the training frequency of both the query country ("Poland") and the in-context city ("London") highly affect the models' likelihood of using the counterfactual. We then use head attribution to identify individual attention heads that either promote the memorized answer or the in-context answer in the logits. By scaling up or down the value vector of these heads, we can control the likelihood of using the in-context answer on new data. This method can increase the rate of generating the in-context answer to 88\% of the time simply by scaling a single head at runtime. Our work contributes to a body of evidence showing that we can often localize model behaviors to specific components and provides a proof of concept for how future methods might control model behavior dynamically at runtime.

Instilling Inductive Biases with Subnetworks

Despite the recent success of artificial neural networks on a variety of tasks, we have little knowledge or control over the exact solutions these models implement. Instilling inductive biases -- preferences for some solutions over others -- into these models is one promising path toward understanding and controlling their behavior. Much work has been done to study the inherent inductive biases of models and instill different inductive biases through hand-designed architectures or carefully curated training regimens. In this work, we explore a more mechanistic approach: Subtask Induction. Our method discovers a functional subnetwork that implements a particular subtask within a trained model and uses it to instill inductive biases towards solutions utilizing that subtask. Subtask Induction is flexible and efficient, and we demonstrate its effectiveness with two experiments. First, we show that Subtask Induction significantly reduces the amount of training data required for a model to adopt a specific, generalizable solution to a modular arithmetic task. Second, we demonstrate that Subtask Induction successfully induces a human-like shape bias while increasing data efficiency for convolutional and transformer-based image classification models.

Deep Neural Networks Can Learn Generalizable Same-Different Visual Relations

Although deep neural networks can achieve human-level performance on many object recognition benchmarks, prior work suggests that these same models fail to learn simple abstract relations, such as determining whether two objects are the same or different. Much of this prior work focuses on training convolutional neural networks to classify images of two same or two different abstract shapes, testing generalization on within-distribution stimuli. In this article, we comprehensively study whether deep neural networks can acquire and generalize same-different relations both within and out-of-distribution using a variety of architectures, forms of pretraining, and fine-tuning datasets. We find that certain pretrained transformers can learn a same-different relation that generalizes with near perfect accuracy to out-of-distribution stimuli. Furthermore, we find that fine-tuning on abstract shapes that lack texture or color provides the strongest out-of-distribution generalization. Our results suggest that, with the right approach, deep neural networks can learn generalizable same-different visual relations.

Circuit Component Reuse Across Tasks in Transformer Language Models

Recent work in mechanistic interpretability has shown that behaviors in language models can be successfully reverse-engineered through circuit analysis. A common criticism, however, is that each circuit is task-specific, and thus such analysis cannot contribute to understanding the models at a higher level. In this work, we present evidence that insights (both low-level findings about specific heads and higher-level findings about general algorithms) can indeed generalize across tasks. Specifically, we study the circuit discovered in Wang et al. (2022) for the Indirect Object Identification (IOI) task and 1.) show that it reproduces on a larger GPT2 model, and 2.) that it is mostly reused to solve a seemingly different task: Colored Objects (Ippolito & Callison-Burch, 2023). We provide evidence that the process underlying both tasks is functionally very similar, and contains about a 78% overlap in in-circuit attention heads. We further present a proof-of-concept intervention experiment, in which we adjust four attention heads in middle layers in order to 'repair' the Colored Objects circuit and make it behave like the IOI circuit. In doing so, we boost accuracy from 49.6% to 93.7% on the Colored Objects task and explain most sources of error. The intervention affects downstream attention heads in specific ways predicted by their interactions in the IOI circuit, indicating that this subcircuit behavior is invariant to the different task inputs. Overall, our results provide evidence that it may yet be possible to explain large language models' behavior in terms of a relatively small number of interpretable task-general algorithmic building blocks and computational components.

NeuroSurgeon: A Toolkit for Subnetwork Analysis

Despite recent advances in the field of explainability, much remains unknown about the algorithms that neural networks learn to represent. Recent work has attempted to understand trained models by decomposing them into functional circuits (Csord\'as et al., 2020; Lepori et al., 2023). To advance this research, we developed NeuroSurgeon, a python library that can be used to discover and manipulate subnetworks within models in the Huggingface Transformers library (Wolf et al., 2019). NeuroSurgeon is freely available at https://github.com/mlepori1/NeuroSurgeon.