David Chanin

David Chanin is a PhD student in the UCL Centre for Doctoral Training in Foundational AI, where he studies mechanistic interpretability and knowledge representation in large language models. He is a researcher at Decode Research and a maintainer of the SAELens library, contributing to open-source tooling for training sparse autoencoders and analyzing neural network internals.

No endorsements yet.

Personal Website

https://chanind.github.io/

LinkedIn

-

Twitter / X

-

LessWrong

-

EA Forum

-

No grants recorded.