#Interpretability

5 items

A Global Workspace in Language Models

article Anthropic · Jul 6, 2026

#global-workspace #consciousness #interpretability
A Global Workspace in Language Models (full paper)

paper Anthropic (Transformer Circuits Thread) · Jul 6, 2026

#global-workspace #consciousness #interpretability
Emergent Introspective Awareness in Large Language Models

paper Jack Lindsey (Anthropic) · Jan 5, 2026

#interpretability #consciousness #global-workspace
Eliciting Latent Predictions from Transformers with the Tuned Lens

paper Nora Belrose et al. · Mar 14, 2023

#interpretability #global-workspace
Interpreting GPT: The Logit Lens

article nostalgebraist · Aug 31, 2020

#interpretability #global-workspace

← Back to all notes