Record · corpus.blog/posts/01a11d3e-f8a3-7057-8cf3-e94ea99c1fff

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

Dan MacKinlay · 1 October 2026 · 3 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 held here: read it at the source, or at its Wayback capture.

Read the post 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
Anchor phrases	0
External links	21
Words captured	632

Cited by

No blog we hold has cited this post yet.

Links from this post

Link

Host

https://github.com/videlalvaro/llm-arithmetic-internals?ref=danmackinlay.name

github.com

Zoom In: An Introduction to Circuits Read at the source

distill.pub

Sparse Crosscoders for Cross-Layer Features and Model Diffing Read at the source

transformer-circuits.pub

Toy Models of Superposition Read at the source

transformer-circuits.pub

Towards Monosemanticity: Decomposing Language Models With Dictionary Learning Read at the source

transformer-circuits.pub

https://www.astralcodexten.com/p/god-help-us-lets-try-to-understand

astralcodexten.com

An Intuitive Explanation of Sparse Autoencoders for LLM Interpretability Read at the source

adamkarvonen.github.io

Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet Read at the source

transformer-circuits.pub

https://www.lesswrong.com/posts/XFLoLzdyeuWDyRZ9q/excursions-into-sparse-autoencoders-what-is-monosemanticity?ref=danmackinlay.name

lesswrong.com

https://www.lesswrong.com/posts/LnHowHgmrMbWtpkxx/intro-to-superposition-and-sparse-autoencoders-colab Who cites this page

lesswrong.com

https://medium.com/@lewingtonpitsos/llm-sparse-autoencoder-embeddings-can-be-used-to-train-nlp-classifiers-3889c32cef6d?ref=danmackinlay.name

medium.com

https://www.alignmentforum.org/posts/NfFST5Mio7BCAQHPA/an-extremely-opinionated-annotated-list-of-my-favourite-1 Who cites this page

alignmentforum.org

A global workspace in language models Read at the source

anthropic.com

https://ai-frontiers.org/articles/the-misguided-quest-for-mechanistic-ai-interpretability Who cites this page

ai-frontiers.org

https://openai.com/blog/multimodal-neurons/ Who cites this page

openai.com

Multimodal Neurons in Artificial Neural Networks Read at the source

distill.pub

Tracing the thoughts of a large language model Read at the source

anthropic.com

Circuit Tracing: Revealing Computational Graphs in Language Models Read at the source

transformer-circuits.pub

On the Biology of a Large Language Model Read at the source

transformer-circuits.pub

https://doi.org/10.48550/arXiv.2410.09087

doi.org

https://doi.org/10.48550/arXiv.2306.00542

doi.org

Elsewhere on danmackinlay.name (4)

Developmental interpretability – The Dan MacKinlay stable of variably-well-consider’d enterprises Read at the source

danmackinlay.name

Model interpretation and explanation – The Dan MacKinlay stable of variably-well-consider’d enterprises Read at the source

danmackinlay.name

AI Safety – The Dan MacKinlay stable of variably-well-consider’d enterprises Read at the source

danmackinlay.name

Causal abstraction – The Dan MacKinlay stable of variably-well-consider’d enterprises Read at the source

danmackinlay.name

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

Cited by

Links from this post

Similar posts