A global workspace in language models \ Anthropic
anthropic.com · 5,117 words · saved by 25 readers
Interpretability research on Claude's internal thoughts.
Interpretability A global workspace in language models Jul 6, 2026 Read the paper As you read this sentence, circuits in your brain are adjusting your posture, controlling your breathing, and transforming lines and curves on the screen into recognizable words. Most of this processing is invisible to you. But some of what takes place in your brain you do have access to—an image that pops into your head, or a deliberate plan you make about where to go shopping. Neuroscientists and philosophers sometimes refer to the latter type of brain activity as “consciously accessible,” to distinguish it fro
saved by
- Anson Yu
- Ratan Kaliani
- Linda
- Emma Guo
- Ayodeji Adesegun
- Yushan Li
- Gloria Ma
- Donald
- Dylan Fridman
- Florent Tavernier
- Alex Yun
- Julia Wu
related reading
- Verbalizable Representations Form a Global Workspace in Language Modelstransformer-circuits.pub
- Tracing the thoughts of a large language model \ Anthropicanthropic.com
- No Space Like J-Space - by Zvi Mowshowitzthezvi.substack.com
- External commentary for global workspace paper -- final finalwww-cdn.anthropic.com
- On the Biology of a Large Language Modeltransformer-circuits.pub
- the j-lens: finding an llm's unspoken concepts / chiragctxnn.github.io
- A Review of Anthropic's Global Workspace Paper — LessWronglesswrong.com
- Mapping the Mind of a Large Language Model \ Anthropicanthropic.com
- Transformer Circuits Threadtransformer-circuits.pub
- Tracing the thoughts of a large language model \ Anthropicanthropic.com
- Emergent introspective awareness in large language models \ Anthropicanthropic.com
- Natural Language Autoencoders \ Anthropicanthropic.com