Transformer Circuits - Decomposing Small Language Models

Can we understand what’s going in Large Language Models by dissecting small ones?

Shea Cardozo
Last updated on Jan 8, 2023 1 min read
Robots in disguise

This post is available here.

Shea Cardozo
Shea Cardozo
PhD Student in Computer Science

Hi! I’m a PhD Student in the Waterloo Intelligent Systems Lab (WISELab) at the University of Waterloo. I am broadly interested in generalization in computer vision and its applications to autonomous systems.