transformer-lens-interpretability
•published 2026/01/24
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.
📦 Install Skill
Command line install
Install directly with the `skills` CLI.
npx skills add zechenzhangAGI/AI-research-SKILLs/04-mechanistic-interpretability/transformer-lensFile Explorer
No file selected
Select a file to view its content