Texonom AI

AI & ML interests

NLP, Taxonomy

Recent Activity

seonglae  authored a paper about 24 hours ago

OptimismBench: Forecasting Bias and the Alignment Effect in Language Model Judgment

seonglae  authored a paper 4 days ago

Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects

seonglae  authored a paper 4 days ago

Control Reinforcement Learning: Interpretable Token-Level Steering of LLMs via Sparse Autoencoder Features

View all activity

Team members 1