Efficient Dictionary Learning With Switch Sparse Autoencoders - Detailed Analysis
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 ... In this video, we dive deep into the world of The paper proposes a method to identify and interpret the directions in activation space of neural networks, addressing the issue ... A visual explanation of how transformers piece concepts together, told in the style of 3Blue1Brown. Introducing SAEs. What truly ... In this video we'll see an online variant of the 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 ...
How do we interpret the embedding spaces of neural networks? This lecture explores techniques for making the algorithms learn ... One of the core roadblocks to understanding the computation inside a transformer is the fact that individual neurons do not seem ... I made a video about one of my favorite papers! I hope you enjoy :) ===Summary=== "Applying
Photo Gallery

![[QA] Efficient Dictionary Learning with Switch Sparse Autoencoders](https://i.ytimg.com/vi/4z9S-URNse0/mqdefault.jpg)






![Neural networks [8.6] : Sparse coding - online dictionary learning algorithm](https://i.ytimg.com/vi/IePxTepLvQc/mqdefault.jpg)




![Hoagy Cunningham — Finding distributed features in LLMs with sparse autoencoders [TAIS 2024]](https://i.ytimg.com/vi/HPLIl9ZOpUQ/mqdefault.jpg)



