Record
- Authors
- Peigné, P.
- Year
- 2023
- Title
- Taking features out of superposition with sparse autoencoders more quickly with informed initialization
- Published in
- LessWrong
- Type
- Web page
- Links
- https://www.lesswrong.com/posts/YJpMgi7HJuHwXTkjk/taking-features-out-of-superposition-with-sparse
- Our note
- none yet
- Verification
- url-ok: the web address responds (the page itself is not checked).
https://www.lesswrong.com/posts/YJpMgi7HJuHwXTkjk/taking-features-out-of-superposition-with-sparse: HTTP 200, checked 2026-11-14 - Id
peigne-2023-taking-features-out-superposition-sparse-autoencoders
Cited on
- Circuits Updates – October 2025 read status: not read
As cited
The pages cite this work in one form.
-
Peigné, P. (2023, September 23). Taking features out of superposition with sparse autoencoders more quickly with informed initialization. LessWrong. https://www.lesswrong.com/posts/YJpMgi7HJuHwXTkjk/taking-features-out-of-superposition-with-sparse (Cited by the item's 3 November edit, which gives the surname only; author and date from LessWrong's record; not read for this note.)
BibLaTeX
@online{peigne-2023-taking-features-out-superposition-sparse-autoencoders,
author = {Peigné, P.},
title = {{Taking features out of superposition with sparse autoencoders more quickly with informed initialization}},
organization = {LessWrong},
date = {2023},
url = {https://www.lesswrong.com/posts/YJpMgi7HJuHwXTkjk/taking-features-out-of-superposition-with-sparse}
}