Can We Read Claude’s Silent Thoughts? Anthropic’s J-Space Explained
Anthropic's 2026 Global Workspace paper claims Claude has a small internal "J-space": verbalizable representations that can be read, edited, and ablated. This is a practitioner-level deep dive into "Verbalizable Representations Form a Global Workspace in Language Models." We break down how the Jacobian Lens differs from logit-lens-style readouts, how J-space is defined, and why Anthropic argues this workspace is causal rather than just a passive monitor. You'll learn: How the Jacobian Lens maps intermediate activations to future verbal behavior What J-space is, and what it is not The five workspace-like properties Anthropic tests Why causal swaps and ablations matter How J-space could help alignment auditing Why this does not prove AI consciousness Chapters: 0:00 - The claim without consciousness hype 1:10 - Transformer setup: residual streams and logit lens 3:00 - Jacobian Lens mechanics 5:45 - What J-space is 7:30 - Five workspace properties 11:00 - Causal evidence: swaps and ablations 13:30 - Structure: middle layers and read/write access 15:05 - Alignment auditing 17:20 - Counterfactual reflection training 18:50 - Practitioner takeaways and failure modes Sources: Paper: https://transformer-circuits.pub/2026... Anthropic summary: https://www.anthropic.com/research/gl... Jacobian Lens repo: https://github.com/anthropics/jacobia... Neuronpedia: https://www.neuronpedia.org/ #AI #MechanisticInterpretability #ClaudeAI

There Is Something Faster Than Light

Inside the Mind of Anthropic CEO Dario Amodei | The Circuit | Extended Interview

How to Build Systems to Actually Achieve Your Goals

You Owe Him
![Yann LeCun's $1B Bet Against LLMs [Part 1]](https://i.ytimg.com/vi/kYkIdXwW2AE/hqdefault.jpg?sqp=-oaymwEjCNACELwBSFryq4qpAxUIARUAAAAAGAElAADIQj0AgKJDeAE=&rs=AOn4CLDbV4izF3i-wxevCVIn7FJjoy1vlA)
Yann LeCun's $1B Bet Against LLMs [Part 1]

CLAUDE CODE ADVANCED FULL COURSE (3 HOURS)

CLAUDE CODE MASTERCLASS 4 HOURS: Build & Sell (2026)

Keynote: After the AI Hype – What’s Real, and What’s Next - Richard Campbell - 2026

How To Use Claude Better Than 99% Of People

FULL DISCUSSION: Google's Demis Hassabis, Anthropic's Dario Amodei Debate the World After AGI | AI1G

CLAUDE COWORK FULL COURSE 3 HOURS For Beginners (2026)

Deep Dive into LLMs like ChatGPT

Is AI Hiding Its Full Power? With Geoffrey Hinton

Violence Expert: Real Self-Defense Is TERRIFYING

12 Important Concepts In the Age of AI Software Development

Ilya Sutskever – We're moving from the age of scaling to the age of research

Why AI Agents are either the best or worst thing we’ve ever built

I got a private lesson on Claude Cowork & Claude Code

Creator of C++: Bell Labs, Negative Overhead Abstraction, Mistakes | Bjarne Stroustrup

