Transformer Lens Interpretability

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.

synthetic-sciences Updated 4.4k repo stars
An OpenScience session comparing EGFR inhibitor potency: the trace shows the search, the written files, the analysis run and the answer with a results table

File contents

synthetic-sciences/openscience commit 5cccd18a91

Frequently asked questions

npx get-skill add synthetic-sciences/transformer-lens-interpretability