222-InterPLM: Interpretable Protein Language Models

The paper introduces "InterPLM," a systematic framework for interpreting protein language models (PLMs) using sparse autoencoders (SAEs). This method successfully extracts thousands of interpretable features from PLMs like ESM-2, revealing biological concepts such as binding sites and functional domains that are stored in superposition within the model's neurons. The research demonstrates that SAE...去小宇宙查看完整单集简介
前往小宇宙评论区与主播互动