Record · anthropic.com
Superposition, memorization, and double descent
Anthropic · 9 September 2026 · 2 min read
A post on anthropic.com, published 9 September 2026, has not been cited by any blog yet (corpus.blog, measured 12 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.
0blogs citing
| Period | Blogs | Links |
|---|---|---|
| All time | 0 | 0 |
| Last 90 days | 0 | 0 |
| Last 30 days | 0 | 0 |
| Last 7 days | 0 | 0 |
| Words blogs link it with | 0 |
|---|---|
| External links | 1 |
| Length | 326 |
Cited by
No blog we hold has cited this post yet.
Links from this post
Similar posts
Notes on Toy Models of Superposition
tylercrosse.com
14 Jul 2026
I Trained a Tiny Network to Compress Data. It Drew a Pentagon.
Towards Data Science
23 Sept 2026
Transformer Circuits Thread Notes
tylercrosse.com
12 Jul 2026
MSE loss does not generate superposition
reasonableapproximation.net
27 Jul 2026
Notes on Towards Monosemanticity and Scaling Monosemanticity
tylercrosse.com
14 Jul 2026
Reading Note: A Theory of Deep Learning
ngrislain.github.io
7 May 2026
Deep Learning: Training Dynamics
Sean's Blog
3 Sept 2026
Developmental interpretability – The Dan MacKinlay stable of variably-well-consider’d enterprises
Dan MacKinlay
1 Oct 2026
Interpolation and extrapolation in neural networks – The Dan MacKinlay stable of variably-well-consider’d enterprises
Dan MacKinlay
1 Oct 2026
Some experiments to help me understand Neural Nets better, post 3 of N – Thomas Dullien
thomasdullien.github.io
17 Sept 2026
Something wrong here? Report a problem