corpus.blog
41,554 blogs · 5,181,941 posts Claim your blog
Record · corpus.blog/posts/01a08219-ddaf-7384-bcb4-f2bfae6856f5

Circuits Updates — January 2024

Transformer Circuits · published 23 January 2024

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at transformer-circuits.pub Wayback capture
1blogs citing
First cited
22 Jun 2024
Most recent
22 Jun 2024
Rank this month
not ranked
External links
21
Words captured
5,490

Cited by

Blog
In the post
Date
thesephist.com
Prism: mapping interpretable concepts and features in a latent space of language Read at the source ↗
22 Jun 2024

Links from this post

Link
Host
https://www.lesswrong.com/posts/wHHdJdhKBqoKAMC5d/expanding-the-scope-of-superposition
lesswrong.com
https://www.lesswrong.com/posts/KicP8fBdHNjZBXxRB/an-ov-coherent-toy-model-of-attention-head-superposition
lesswrong.com
https://s3-frontend.infra.ant.dev/anthropic-serve/colah/drafts/monosemantic-features/index.html
s3-frontend.infra.ant.dev
https://www.lesswrong.com/posts/wqRqb7h6ZC48iDgfK/tentatively-found-600-monosemantic-features-in-a-small-lm
lesswrong.com
https://www.lesswrong.com/posts/eDicGjD9yte6FLSie/interpreting-neural-networks-through-the-polytope-lens
lesswrong.com
https://arxiv.org/abs/2310.15916
arxiv.org
https://functions.baulab.info/
functions.baulab.info
https://arxiv.org/abs/2305.13673
arxiv.org
https://arxiv.org/abs/2311.08360
arxiv.org
https://arxiv.org/abs/2210.01117
arxiv.org
https://arxiv.org/abs/2306.17844
arxiv.org
https://arxiv.org/abs/2301.05217
arxiv.org
https://www.harvard.edu/kempner-institute/2023/11/14/where-do-features-come-from-a-story-of-sinusoids-and-inductive-biases/
harvard.edu
https://arxiv.org/abs/2302.03025
arxiv.org
https://arxiv.org/abs/2211.15661
arxiv.org
https://arxiv.org/abs/2106.06981
arxiv.org
https://arxiv.org/abs/2310.16028
arxiv.org
https://en.wikipedia.org/wiki/Solomonoff%27s_theory_of_inductive_inference
en.wikipedia.org
https://www.lesswrong.com/posts/iGuwZTHWb6DFY3sKB/fact-finding-attempting-to-reverse-engineer-factual-recall
lesswrong.com
https://arxiv.org/abs/2309.08600
arxiv.org
https://www.lesswrong.com/posts/DtdzGwFh9dCfsekZZ/sparse-autoencoders-work-on-attention-layer-outputs
lesswrong.com
Elsewhere on transformer-circuits.pub (7)