Media Summary: Warning: This is an ad-libbed talk, and I'm sure I got some facts wrong. This is a talk I gave to my MATS 9.0 training program on ... This has been my favorite video so far to make! I think interpretability is so important both in terms of ensuring safe AI and also ... One of the core roadblocks to understanding the computation inside a transformer is the fact that individual neurons do not seem ...
Sparse Autoencoders Progress Limitations With Joshua Engels - Detailed Analysis & Overview
Warning: This is an ad-libbed talk, and I'm sure I got some facts wrong. This is a talk I gave to my MATS 9.0 training program on ... This has been my favorite video so far to make! I think interpretability is so important both in terms of ensuring safe AI and also ... One of the core roadblocks to understanding the computation inside a transformer is the fact that individual neurons do not seem ... Nemotron Labs is where NVIDIA researchers work on what open models can do next and in this livestream, we hear directly from ... Intuitive and mechanical descriptions of how In this AI Research Roundup episode, Alex discusses the paper: 'A Mechanistic Investigation of Supervised Fine Tuning' This ...
![Hoagy Cunningham — Finding distributed features in LLMs with sparse autoencoders [TAIS 2024]](https://i.ytimg.com/vi/HPLIl9ZOpUQ/mqdefault.jpg)
