Exploring J-space Structure in Mechanistic Interpretability
rickasaurus · x · 2026-07-07
Prominent interpretability account teortaxesTex initiated a discussion on J-space (a mechanistic interpretability concept): How is J-space measured? How does its structure interact with model capabilities? And at what stage of training does it emerge?
The thread focuses on understanding the relationship between a model's internal representations and the emergence of its capabilities.
Related event: Anthropic Discovers Global Workspace Inside Claude(102 posts)→
More from Research
- New review: how prefrontal cortex dynamics turn world models into flexible behavior — AnnaCiaunica · 2026-10-27
- LIBERO-MAX: Robot Policies Drop 11–26 Points When the World Changes Mid-Task — drmapavone · 2026-10-27
- Kolab Benchmark Uses Pro Screen Recordings to Show AI Agents Overestimate Collaboration Quality — minnesotanlp · 2026-10-27
- One BBQ Example Pushes LLM Fairness Scores Past 90%, EMNLP Paper Questions Benchmarks — radamihalcea · 2026-10-27
- Real2Sem2Real turns one phone video into 2,000+ robot demos, matching 150 teleop demos — Scobleizer · 2026-10-27
- Understanding MuonH (Hyperball) through weight norm geometry of scale-invariant networks — jasondeanlee · 2026-10-27