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.

bishal-pdMSFT Updated 0 repo stars

File contents

bishal-pdMSFT/msb-skills commit 6f9320ec1f

Frequently asked questions

npx get-skill add bishal-pdmsft/transformer-lens-interpretability