ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs

Add code
May 23, 2025
Figure 1 for ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs
Figure 2 for ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs
Figure 3 for ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs
Figure 4 for ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs

Share this with someone who'll enjoy it:

View paper onarxiv icon

Share this with someone who'll enjoy it: