Anthropic's J-Space paper / Representations in LLMs

​Anthropic’s J-space research uses a Jacobian lens to reveal concepts a language model processes internally without putting them into words. Let’s have a look under the hood and discuss the evidence for a shared workspace for reasoning.

​The paper comes with a blog post that may be easier to read: https://www.anthropic.com/research/global-workspace

​Find the paper here: https://arxiv.org/abs/2607.15495

​

​---

​

​We are trying out a new Location -- right at the Westbahnhof IKEA. Take the elevator to the fifth. We may relocate if it is too crowded. Please Text me if you are late and can't find us.

​---

​

​Bring your own printout or pdf-on-a-gadget. If you didn't have the time to read the whole paper, it is sufficient to be able to pretend to have sort of skimmed it.

​

​---

​

​Want to suggest a paper, an event location, or just stay in touch with regular members? We hang out at the following Matrix server: https://matrix.to/#/%23pwl-wien:rend.al