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
- Nature paper images cellular activity across all organs, revealing body-wide circuits — arjunrajlab · 2026-09-11
- SignNet 1M Dataset Released for Sign Language Research — ducha_aiki · 2026-09-11
- ECCV26 Oral: Flow Matching Enables Single-Stage Multi-View Point Cloud Registration — ducha_aiki · 2026-09-11
- InFlux++ Method Released — ducha_aiki · 2026-09-11
- Skyfall GS Uses Flux to Refine Gaussian Splatting, Accepted at ECCV 2026 — ducha_aiki · 2026-09-11
- Could 10k agents discover learning methods beyond backprop, or just tweak existing ones? — SeunghyunSEO7 · 2026-09-11