Episode
[Linkpost] "Interpreting Language Model Parameters" by Lucius Bushnaq, Dan Braun, Oliver Clive-Griffin, Bart Bussmann, Nathan Hu, mivanitskiy, Linda Linsefors, Lee Sharkey
- Published
- May 7, 2026
- Duration seconds
- 277
- Processing state
not_requested
Actions
POST https://stenobird.com/v1/public/podcasts/lesswrong-curated-popular-5643401/episodes/linkpost-interpreting-language-model-parameters-by-lucius-bushnaq-dan-braun-oliver-clive-griffin-bart-bussmann-nathan-hu-mivanitskiy-linda-linsefors-lee-sharkey/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/lesswrong-curated-popular-5643401/linkpost-interpreting-language-model-parameters-by-lucius-bushnaq-dan-braun-oliver-clive-griffin-bart-bussmann-nathan-hu-mivanitskiy-linda-linsefors-lee-sharkey.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
This is a link post. This is the latest work in our Parameter Decomposition agenda. We introduce a new parameter decomposition method, adVersarial Parameter Decomposition (VPD)[1] and decompose the parameters of a small[2] language model with it. VPD greatly improves on our previous techniques, Stochastic Parameter Decomposition (SPD) and Attribution-based Parameter Decomposition (APD). We think the parameter decomposition approach is now more-or-less ready to be applied at scale to models...