Researcher: J-lens Approximates LLM's Cognitively Accessible Privileged Representations
rgblong · x · 2026-07-07
Researcher rgblong points out that there exists a set of "cognitively accessible" privileged representations within LLMs, and that J-lens provides a good approximation of this set. They consider this discovery to be quite significant and remarkable in its own right.
Related event: Anthropic Discovers Global Workspace Inside Claude(102 posts)→
More from Research
- Nature Physics: reprogrammable refractive index enables arbitrary multimode wave control for ML — MarioKrenn6240 · 2026-10-27
- Wakaru open-sources ontologize: labeling datasets from model activations — amplifiedamp · 2026-10-27
- EMNLP Oral paper traces multilingual representations in LLMs with cross-layer transcoders — ZhijingJin · 2026-10-27
- GPT-6 Pro reruns crime research: GTA V's 2013 launch tied to violence dips in four regions — emollick · 2026-10-27
- OpenAI's Aaron Lou on leaving a Stanford PhD for OpenAI, diffusion LMs vs autoregression — aaron_lou · 2026-10-27
- CLT-Forge: Open-source toolkit for cross-layer transcoder training and attribution graphs — ZhijingJin · 2026-10-27