Skip to content
corpus.blogBeta
Sign in Claim your blog
Record · seantrott.substack.com

"Mechanistic interpretability" for LLMs, explained

seantrott.substack.com · 8 July 2024 · 28 min read

A post on seantrott.substack.com, published 8 July 2024, is cited by 2 distinct blogs to date (corpus.blog, measured 16 October 2026).

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

Read at seantrott.substack.com (opens in a new tab) Wayback capture (opens in a new tab)

2blogs citing

Citing blogs and links by period
Period Blogs Links
All time22
Last 90 days00
Last 30 days00
Last 7 days00
Figures for this page
First cited13 Sept 2024
Latest citation5 May 2025
Words blogs link it with1
External links42
Length6,269

Words blogs link it with

The words blogs link this page with, by how many different blogs use them.

  • mechanistic interpretability2 blogs

Cited by 2 blogs in 2 posts

One row per blog, the most recently citing first. Each shows the blog's newest citing post; open a row for the others.

Links from this post

Link
https://www.insidehighered.com/news/tech-innovation/artificial-intelligence/2024/05/17/new-chatgpt-eyed-better-learning Who cites this page
insidehighered.com
https://www.nature.com/articles/s41586-023-06792-0 Who cites this page
nature.com
https://en.wikipedia.org/wiki/Black_box Who cites this page
en.wikipedia.org
Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet Read at transformer-circuits.pub (opens in a new tab)
transformer-circuits.pub
Large language models, explained with a minimum of math and jargon Read at understandingai.org (opens in a new tab)
understandingai.org
https://www.understandingai.org/ Who cites this page
understandingai.org
How To Become A Mechanistic Interpretability Researcher — AI Alignment Forum Read at neelnanda.io (opens in a new tab)
neelnanda.io
https://arena3-chapter1-transformer-interp.streamlit.app/ Who cites this page
arena3-chapter1-transformer-interp.streamlit.app
https://committees.parliament.uk/writtenevidence/127070/pdf/ Who cites this page
committees.parliament.uk
http://a16z.com Who cites this page
a16z.com
https://committees.parliament.uk/committee/170/communications-and-digital-committee/ Who cites this page
committees.parliament.uk
https://www.neelnanda.io/about Read at neelnanda.io (opens in a new tab)
neelnanda.io
https://x.com/NeelNanda5/status/1799203292066558403 Who cites this page
x.com
https://a16z.com/big-ideas-in-tech-2024/ Who cites this page
a16z.com
Anthropic decoded the vectors Claude uses to represent abstract concepts Read at understandingai.org (opens in a new tab)
understandingai.org
https://arxiv.org/abs/2211.00593?ref=bounded-regret.ghost.io Who cites this page
arxiv.org
https://www.redwoodresearch.org/ Who cites this page
redwoodresearch.org
https://arxiv.org/pdf/2405.00208 Who cites this page
arxiv.org
https://arxiv.org/pdf/1905.05950 Who cites this page
arxiv.org
https://direct.mit.edu/coli/article/48/1/207/107571/Probing-Classifiers-Promises-Shortcomings-and Who cites this page
direct.mit.edu
https://proceedings.neurips.cc/paper_files/paper/2022/file/6f1d43d5a82a37e89b0665b33bf3a182-Paper-Conference.pdf Who cites this page
proceedings.neurips.cc
https://github.com/TransformerLensOrg/TransformerLens Who cites this page
github.com
Towards Monosemanticity: Decomposing Language Models With Dictionary Learning Read at transformer-circuits.pub (opens in a new tab)
transformer-circuits.pub
https://en.wikipedia.org/wiki/The_Library_of_Babel Who cites this page
en.wikipedia.org
Toy Models of Superposition Read at transformer-circuits.pub (opens in a new tab)
transformer-circuits.pub
https://en.wikipedia.org/wiki/Autoencoder Who cites this page
en.wikipedia.org
https://en.wikipedia.org/wiki/Regularization_(mathematics Who cites this page
en.wikipedia.org
https://transformer-circuits.pub/2024/scaling-monosemanticity/features/index.html?featureId=34M_31164353 Who cites this page
transformer-circuits.pub
https://transformer-circuits.pub/2024/scaling-monosemanticity/features/index.html?featureId=34M_9493533 Who cites this page
transformer-circuits.pub
https://transformer-circuits.pub/2024/scaling-monosemanticity/features/index.html?featureId=1M_887839 Who cites this page
transformer-circuits.pub
https://transformer-circuits.pub/2024/scaling-monosemanticity/features/index.html?featureId=1M_3 Who cites this page
transformer-circuits.pub
Golden Gate Claude Read at anthropic.com (opens in a new tab)
anthropic.com
https://www.sciencedirect.com/science/article/pii/S0959438804001035?casa_token=LrAaUmKqWWUAAAAA:qaqOVcP0mWwCV9P6e9JvxlolYPy66AabkZTb68J9ZZyA0uR1_m30n3zDMxgdC4jLR1JmO7Papg Who cites this page
sciencedirect.com
Interpretability Dreams Read at transformer-circuits.pub (opens in a new tab)
transformer-circuits.pub
Text Is the Universal Interface Read at scale.com (opens in a new tab)
scale.com
https://arxiv.org/abs/2310.12611 Who cites this page
arxiv.org
https://arxiv.org/pdf/2310.01405 Who cites this page
arxiv.org
https://plato.stanford.edu/entries/computational-mind/ Who cites this page
plato.stanford.edu
Reflections on Qualitative Research Read at transformer-circuits.pub (opens in a new tab)
transformer-circuits.pub
https://www.lesswrong.com/posts/LNA8mubrByG7SFacm/against-almost-every-theory-of-impact-of-interpretability-1 Who cites this page
lesswrong.com
https://www.lesswrong.com/posts/tEPHGZAb63dfq2v8n/how-useful-is-mechanistic-interpretability Who cites this page
lesswrong.com
https://pdrivier.github.io/about/
pdrivier.github.io
Elsewhere on seantrott.substack.com (4)

Looking for more like this? Find posts and blogs like it
Something wrong here? Report a problem