Media Summary: 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 ... I made a video about one of my favorite papers! I hope you enjoy :) === 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 ...
Matryoshka Nested Sparse Autoencoders Explained - Detailed Analysis & Overview
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 ... I made a video about one of my favorite papers! I hope you enjoy :) === 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 ... Data around us, like images and documents, are very high dimensional. One of the core roadblocks to understanding the computation inside a transformer is the fact that individual neurons do not seem ... In this video, Alejandro (Alexander), Founding Engineer at ZeroEntropy, explains what
In this video, we're going to learn about
![Hoagy Cunningham — Finding distributed features in LLMs with sparse autoencoders [TAIS 2024]](https://i.ytimg.com/vi/HPLIl9ZOpUQ/mqdefault.jpg)
