🏗️ Building on HF

Seonglae Cho

seonglae

·

https://www.seongland.com

AI & ML interests

NLP, Humanoid, AGI

Recent Activity

authored a paper about 4 hours ago

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

authored a paper about 4 hours ago

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

upvoted a paper about 5 hours ago

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

View all activity

Organizations

seonglae 's papers 7

arxiv:2607.20596

arxiv:2602.10437

arxiv:2602.08159

arxiv:2508.12535

arxiv:2506.17673

arxiv:2505.08842

arxiv:2310.13895