Towards Monosemanticity: Decomposing Language Models With Dictionary Learning

Record

Authors
Bricken, T.; Templeton, A.; Batson, J.; et al.
Year
2023
Title
Towards Monosemanticity: Decomposing Language Models With Dictionary Learning
Published in
Transformer Circuits Thread
Type
Web page
Links
https://transformer-circuits.pub/2023/monosemantic-features/index.html
Our note
Towards Monosemanticity: Decomposing Language Models With Dictionary Learning
Verification
url-ok: the web address responds (the page itself is not checked).
https://transformer-circuits.pub/2023/monosemantic-features/index.html: HTTP 200, checked 2026-11-14
Id
bricken-2023-towards-monosemanticity-decomposing-language-models-dictionary

Cited on

As cited

The pages cite this work in 7 forms.

  • Bricken, T., Templeton, A., Batson, J., et al. (2023). Towards Monosemanticity: Decomposing Language Models With Dictionary Learning. Transformer Circuits Thread. https://transformer-circuits.pub/2023/monosemantic-features/index.html
  • Bricken, T., Templeton, A., Batson, J., Chen, B., Jermyn, A., Conerly, T., Turner, N. L., Anil, C., Denison, C., Askell, A., Lasenby, R., Wu, Y., Kravec, S., Schiefer, N., Maxwell, T., Joseph, N., Tamkin, A., Nguyen, K., McLean, B., Burke, J. E., Hume, T., Carter, S., Henighan, T., and Olah, C. (2023). Towards Monosemanticity: Decomposing Language Models With Dictionary Learning. Transformer Circuits Thread. https://transformer-circuits.pub/2023/monosemantic-features/index.html. Section names in this note refer to this web version.
  • Bricken, T., Templeton, A., Batson, J., Chen, B., Jermyn, A., et al. (2023). Towards Monosemanticity: Decomposing Language Models With Dictionary Learning. Transformer Circuits Thread. https://transformer-circuits.pub/2023/monosemantic-features/index.html
  • Bricken, T., Templeton, A., Batson, J., Chen, B., Jermyn, A., et al. (2023). Towards Monosemanticity: Decomposing Language Models With Dictionary Learning. Transformer Circuits Thread. https://transformer-circuits.pub/2023/monosemantic-features/index.html. Cited for its references back to this update ("How can we tell if the autoencoder is working?", "Future Work", the discussion of superposition theories, and the appendix on training sparse autoencoders).
  • Bricken, T., Templeton, A., Batson, J., Chen, B., Jermyn, A., et al. (2023). Towards Monosemanticity: Decomposing Language Models With Dictionary Learning. Transformer Circuits Thread. https://transformer-circuits.pub/2023/monosemantic-features/index.html. Cited for its summary of results, "Universality", "Feature Splitting" and "Future Work".
  • Bricken, T., Templeton, A., Batson, J., et al. (2023). Towards Monosemanticity: Decomposing Language Models With Dictionary Learning. Transformer Circuits Thread. https://transformer-circuits.pub/2023/monosemantic-features/index.html. Cited for its randomly initialized model control ("Do features tell us about the model or the data?").
  • Bricken, T., Templeton, A., Batson, J., et al. (2023). Towards Monosemanticity: Decomposing Language Models With Dictionary Learning. Transformer Circuits Thread. https://transformer-circuits.pub/2023/monosemantic-features/index.html. Cited for its references to this update ("Related Work", "Future Work", "What makes a good decomposition?").

BibLaTeX

@online{bricken-2023-towards-monosemanticity-decomposing-language-models-dictionary,
  author = {Bricken, T. and Templeton, A. and Batson, J. and others},
  title = {{Towards Monosemanticity: Decomposing Language Models With Dictionary Learning}},
  organization = {Transformer Circuits Thread},
  date = {2023},
  url = {https://transformer-circuits.pub/2023/monosemantic-features/index.html}
}

Download · JSON with CSL-JSON · the whole bibliography