Path Patching

Creator

Creator

Created

Created

2025 Feb 1 22:5

Editor

Editor

Edited

Edited

2025 Feb 1 22:9

Refs

Refs

For a pair of components, we patch in the clean output of component 1, but only along paths that affect the input of component 2.

A Comprehensive Mechanistic Interpretability Explainer & Glossary - Dynalist

Dynalist lets you organize your ideas and tasks in simple lists. It's powerful, yet easy to use. Try the live demo now, no need to sign up.

A Comprehensive Mechanistic Interpretability Explainer & Glossary - Dynalist

https://dynalist.io/d/n2ZWtnoYHrU1s4vnFSAQ519J#z=0CzxbHpOoT6L2aWXQ36xiIWw

Recommendations

///////////