4min 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 Automate the Process of Isolating Subgraphs

Just seems like there is intuition here around things like you know the best way to explain the flight of a fly ball is not to go to the quantum mechanical level. In some sense it's like you're optimizing for the human audience's ability to understand the results as much as anything else. How hard is that from a coding standpoint or a notation standpoint? I feel like I would have a hard time going from okay we've decided we want to zoom in on the attention head level or you know the nml individual mlp blocks will be our kind of unit of consideration and then actually figuring out how do I express that in code as a causal acyclic graph.

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