Neel Nanda

mechanistic interpretability (3) sparse autoencoder (3) linear representation (2) imitation learning (1) sentiment analysis (1) model calibration (1) bayesian inference (1) policy learning (1) neural network interpretability (1) model analysis (1) group theory (1) model interpretability (1) latent representation (1) language model (1) world model (1) circuit analysis (1) feature decomposition (1) self-supervised learning (1) feature extraction (1) online learning (1)