Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs

Finetuning language models on small, curated datasets is standard practice for adapting them to specific policies or domains. We show that finetuning on narrow, factually-defensible, moderation-passing data can cause broad ideological shifts across unrelated domains, while preserving general capabilities. Training GPT-4.1 on right- or left-leaning economics Q&A yields matched ideological shifts on topics such as criminal justice, the environment, and cultural taste. The same effect appears with plausibly-deployed datasets such as workplace HR policy and practical finance queries, as well as on a science-pseudoscience axis where food-safety finetuning increases sycophantic agreement with users expressing false health beliefs. We call this phenomenon ideological generalisation and propose a methodology to measure two properties: breadth, how far the shift reaches across topics absent from training, and amplification, how much finetuning intensifies the shift relative to few-shot prompting on the same examples. We show that few-shot prompting indicates the direction of generalisation but finetuning pushes the model to further extremes, including to far out-of-distribution outputs such as endorsements of race-IQ connections and political violence. The effect replicates on Gemma-3, holds under judge-free evaluations and external benchmarks, survives mixing with generic data, and leaves GSM8K accuracy within $\pm 1$pp of the baseline.

Moral Preferences of LLMs Under Directed Contextual Influence

Moral benchmarks for LLMs typically use context-free prompts, implicitly assuming stable preferences. In deployment, however, prompts routinely include contextual signals such as user requests, cues on social norms, etc. that may steer decisions. We study how directed contextual influences reshape decisions in trolley-problem-style moral triage settings. We introduce a pilot evaluation harness for directed contextual influence in trolley-problem-style moral triage: for each demographic factor, we apply matched, direction-flipped contextual influences that differ only in which group they favor, enabling systematic measurement of directional response. We find that: (i) contextual influences often significantly shift decisions, even when only superficially relevant; (ii) baseline preferences are a poor predictor of directional steerability, as models can appear baseline-neutral yet exhibit systematic steerability asymmetry under influence; (iii) influences can backfire: models may explicitly claim neutrality or discount the contextual cue, yet their choices still shift, sometimes in the opposite direction; and (iv) reasoning reduces average sensitivity, but amplifies the effect of biased few-shot examples. Our findings motivate extending moral evaluations with controlled, direction-flipped context manipulations to better characterize model behavior.

Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video

Robust tooling and publicly available pre-trained models have helped drive recent advances in mechanistic interpretability for language models. However, similar progress in vision mechanistic interpretability has been hindered by the lack of accessible frameworks and pre-trained weights. We present Prisma (Access the codebase here: https://github.com/Prisma-Multimodal/ViT-Prisma), an open-source framework designed to accelerate vision mechanistic interpretability research, providing a unified toolkit for accessing 75+ vision and video transformers; support for sparse autoencoder (SAE), transcoder, and crosscoder training; a suite of 80+ pre-trained SAE weights; activation caching, circuit analysis tools, and visualization tools; and educational resources. Our analysis reveals surprising findings, including that effective vision SAEs can exhibit substantially lower sparsity patterns than language SAEs, and that in some instances, SAE reconstructions can decrease model loss. Prisma enables new research directions for understanding vision model internals while lowering barriers to entry in this emerging field.

Steering CLIP's vision transformer with sparse autoencoders

While vision models are highly capable, their internal mechanisms remain poorly understood -- a challenge which sparse autoencoders (SAEs) have helped address in language, but which remains underexplored in vision. We address this gap by training SAEs on CLIP's vision transformer and uncover key differences between vision and language processing, including distinct sparsity patterns for SAEs trained across layers and token types. We then provide the first systematic analysis on the steerability of CLIP's vision transformer by introducing metrics to quantify how precisely SAE features can be steered to affect the model's output. We find that 10-15\% of neurons and features are steerable, with SAEs providing thousands more steerable features than the base model. Through targeted suppression of SAE features, we then demonstrate improved performance on three vision disentanglement tasks (CelebA, Waterbirds, and typographic attacks), finding optimal disentanglement in middle model layers, and achieving state-of-the-art performance on defense against typographic attacks.