Record · danmackinlay.name

Developmental interpretability – The Dan MacKinlay stable of variably-well-consider’d enterprises

Dan MacKinlay · 1 October 2026 · 5 min read

A post on danmackinlay.name, published 1 October 2026, has not been cited by any blog yet (corpus.blog, measured 10 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 danmackinlay.name Wayback capture

0blogs citing

Citing blogs and links by period
Period	Blogs	Links
All time	0	0
Last 90 days	0	0
Last 30 days	0	0
Last 7 days	0	0

Figures for this page
Words blogs link it with	0
External links	24
Length	1,096

Cited by

No blog we hold has cited this post yet.

Links from this post

Link

Host

Toy Models of Superposition Read at transformer-circuits.pub

transformer-circuits.pub

https://icmlviz.github.io/icmlviz2016/assets/papers/24.pdf

icmlviz.github.io

https://singularlearningtheory.com/?ref=danmackinlay.name

singularlearningtheory.com

https://www.lesswrong.com/w/singular-learning-theory?ref=danmackinlay.name

lesswrong.com

https://www.alignmentforum.org/s/czrXjvCLsqGepybHC?ref=danmackinlay.name

alignmentforum.org

http://therisingsea.org/notes/metauni/slt20.pdf?ref=danmackinlay.name

therisingsea.org

https://www.liamcarroll.au/mathematics/SLT/?ref=danmackinlay.name

liamcarroll.au

https://cameronrwolfe.me/blog/critical-learning-periods?ref=danmackinlay.name

cameronrwolfe.me

https://rainbowserpent.dev/?experiment=exp_20250811_031851&dataset=dm_mathematics&pattern=Induction&camPos=9.13%2C16.22%2C50.61&camTarget=2.63%2C7.48%2C10.18&ref=danmackinlay.name

rainbowserpent.dev

https://devinterp.com/

devinterp.com

https://www.lesswrong.com/posts/HFcriD29cw3E5QLCR/selective-regularization-for-alignment-focused?ref=danmackinlay.name

lesswrong.com

https://arxiv.org/abs/1711.08856 Who cites this page

arxiv.org

https://proceedings.neurips.cc/paper_files/paper/2023/hash/59404fb89d6194641c69ae99ecdf8f6d-Abstract-Conference.html

proceedings.neurips.cc

https://doi.org/10.48550/arXiv.2209.10652

doi.org

https://doi.org/10.18653/v1/2024.acl-long.834

doi.org

https://proceedings.neurips.cc/paper_files/paper/2022/hash/dfc310e81992d2e4cedc09ac47eff13e-Abstract-Conference.html

proceedings.neurips.cc

https://doi.org/10.1073/pnas.2310002121

doi.org

https://doi.org/10.48550/arXiv.2506.12965

doi.org

https://doi.org/10.23915/distill.00024.001 Who cites this page

doi.org

https://doi.org/10.1016/j.semcdb.2025.103620

doi.org

http://arxiv.org/abs/2011.12428

arxiv.org

https://doi.org/10.48550/arXiv.2506.17809

doi.org

https://doi.org/10.18653/v1/2022.bigscience-1.11

doi.org

https://doi.org/10.48550/arXiv.2508.00331

doi.org

Elsewhere on danmackinlay.name (7)

Mechanistic interpretability – The Dan MacKinlay stable of variably-well-consider’d enterprises Read at danmackinlay.name

danmackinlay.name

https://danmackinlay.name/notebook/nn_scaling_laws.html

danmackinlay.name

https://danmackinlay.name/notebook/statistical_mechanics_of_statistics.html

danmackinlay.name

World models arising in foundation models. – The Dan MacKinlay stable of variably-well-consider’d enterprises Read at danmackinlay.name

danmackinlay.name

Singular Learning Theory – The Dan MacKinlay stable of variably-well-consider’d enterprises Read at danmackinlay.name

danmackinlay.name

Degrees of freedom in NNs – The Dan MacKinlay stable of variably-well-consider’d enterprises Read at danmackinlay.name

danmackinlay.name

Disentangled representation learning – The Dan MacKinlay stable of variably-well-consider’d enterprises Read at danmackinlay.name

danmackinlay.name

Developmental interpretability – The Dan MacKinlay stable of variably-well-consider’d enterprises

Cited by

Links from this post

Similar posts