Verified record · from the answer index
transformer-lens-interpretability
skilltested · static-verifiedscore 49/100signed passport ✓910 uses
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 patte
Declared tools (1)
transformer-lens-interpretability
skill:orchestra-research/ai-research-skills/transformer-lens-interpretability · published by orchestra-research · source repository