Transformer Circuits Thread
Shares rank 6 of 7 research papers by recommenders
Anthropic's free research publication series on mechanistic interpretability, explaining its approach in detail, and people recommend it as a reference point for the field.
Anthropic's free research publication series on mechanistic interpretability, explaining its approach in detail, and people recommend it as a reference point for the field.
5 people gave an opinion
- recommend it
- 5
- criticize it
- 0
- approval share
- 100%
Recommended in 4 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: not recommended
- April 2026: not recommended
- May 2026: recommended
- June 2026: recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 5 people recommend itNeeds 10 or more, not met.
- Nobody criticizes itNeeds 2 to 1 or better, met.
- Recommended in 4 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Good interpretability research
“mechanistic interpretability is a pretty interesting peephole into this general vein”
Comment from 2 Sep 2026 in “The Emergent Symbolic Structure of Artificial Neural Networks” “That looks like good work but not a deep understanding.”
Comment from 11 Sep 2026 on Hacker News
Other research papers people recommend
The four most recommended other research papers, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| The Ironies of Automation by Lisanne Bainbridge | 14 | 0 | 100% | 7 | — | Approved |
| Attention Is All You Need by Vaswani et al. | 14 | 2 | 88% | 7 | — | Approved |
| Structured Programming with go to Statementsby Donald Knuth | 7 | 1 | 88% | 4 | — | — |
| MapReduce: Simplified Data Processing on Large Clusters by Dean and Ghemawat | 6 | 1 | 86% | 5 | — | — |
| Transformer Circuits ThreadThis page | 5 | 0 | 100% | 4 | — | — |
What people said
All 5 comments that mention it, newest first. Each links to the original comment.
“Reading https://transformer-circuits.pub in chronological order might provide that reference point.”
“That looks like good work but not a deep understanding.”
“mechanistic interpretability is a pretty interesting peephole into this general vein”
“transformer-circuits.pub is the OG”
“go directly to the transformer circuits blog, where they explain their approach more in detail”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.