Lex Fridman Podcast
#452 – Dario Amodei: Anthropic CEO on Claude, AGI & the Future of AI & Humanity
you might think of sparse autoencoders as being kind of like a telescope. They allow us to look out and see all these features that are out there. And as we build better and better sparse autoencoders, get better and better at dictionary learning, we see more and more stars. And we zoom in on smaller and smaller stars.
0
💬
0
Comments
Log in to comment.
There are no comments yet.