RSam Podcast cover image

Mechanistic Interpretability and How LLMs Understand

RSam Podcast

00:00

Empirical examples: Golden Gate feature

Pierre describes Anthropic's Golden Gate Bridge feature as a unified, causal representation across modalities and languages.

Play episode from 44:03
Transcript

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app