AXRP - the AI X-risk Research Podcast cover image

19 - Mechanistic Interpretability with Neel Nanda

AXRP - the AI X-risk Research Podcast

CHAPTER

Using Contextual Information in Model Composition

Small dimension well subspace yeah yes small small dimensional you can kind of think of this as the residual stream let's say a thousand dimensional vector and we just cut off the first 50 ignore everything else yep but the network can choose whatever coordinate system involves. This means that the head can choose different subspaces of the destination or source residual streams to pick up on if it so chooses  This lets the model kind of choose different bits to compose with and this matters because one of the things that mechanistic determinability tries hard to exploit is the fact that model computation often seems kind of sparse where there are only some masses.

00:00
Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner