🏗️ Building on HF

Seonglae Cho

seonglae

·

https://www.seongland.com

AI & ML interests

NLP, Humanoid, AGI

Recent Activity

authored a paper about 21 hours ago

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

authored a paper about 21 hours ago

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

upvoted a paper about 21 hours ago

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

View all activity

Organizations

seonglae 's Spaces 10

Automata from Agent Traces

Explore LLM agent behavior as an interactive state machine

OptimismBench

AgentRoom

Watch two AI agents code together in a shared workspace

Confidence Manifold

Control Reinforcement Learning

Explore LLM token decisions with feature‑driven visualizations

CorrSteer: Correlation-Based Steering of Language Models via Sparse Autoencoders

Steer language model output by clicking visual layers

PaaT: Probe as a Tool for Proprioceptive Language Agents

Agent State Graph — Dashboard

Yokhal

Resrer Demo