3min chapter

"The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis cover image

E48: Mechanizing Mechanistic Interpretability with Arthur Conmy

"The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis

CHAPTER

How to Make Mechanistic Interpretability of Generative Language Models Easier

We tried to make our library like well written for all practitioners by building it on top of a re-grace mechanistic interpretability library called a transformer lens. The acdc library can load any of the models that are in the transformer lens library as a computational car with all the connections between the like nodes as different edges. We think that probably acDC will be a little bit too slow on these larger models for now but we're excited to uh future work and scale it up.

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode