56,966 blogs · 4,417,066 posts Claim your blog

Record · corpus.blog/posts/01a0d51d-41c5-709f-ad03-4e968a7df3ce

WorkspaceBench: Evaluating Interpretability Methods for the Global Workspace

AI Alignment Forum · published 23 September 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 alignmentforum.org Wayback capture

0blogs citing

First cited: —
Most recent: —
Rank this month: not ranked
Links from this post: 13
Words captured: 4,972

Cited by

No blog we hold has cited this post yet.

Links from this post

Link

Host

Verbalizable Representations Form a Global Workspace in Language Models Read at the source ↗

transformer-circuits.pub

https://github.com/camilablank/workspace-bench

github.com

https://www.lesswrong.com/posts/eRmzz8J8Qkzqvzrgg/astra-can-do-a-concerning-amount-with-no-chain-of-thought

lesswrong.com

https://www.lesswrong.com/posts/6ek6n7yZ5DzfarJHy/towards-surfacing-model-algorithms-with-meta-tokens-in-the-j

lesswrong.com

https://www.lesswrong.com/posts/AcKRB8wDpdaN6v6ru/interpreting-gpt-the-logit-lens

lesswrong.com

https://transformer-circuits.pub/2026/workspace/

transformer-circuits.pub

https://www.lesswrong.com/posts/nv8oedrnLXKRzNEL9/r-lens-making-j-lens-more-faithful-on-early-layers

lesswrong.com

https://arxiv.org/abs/2303.08112

arxiv.org

https://transformer-circuits.pub/2026/nla/

transformer-circuits.pub

https://arxiv.org/abs/2309.08600

arxiv.org

https://arxiv.org/abs/2401.06102

arxiv.org

https://huggingface.co/agu18dec/olens_and_ar

huggingface.co

https://alignment.anthropic.com/2026/chive/

alignment.anthropic.com