🏗️ Building on HF

Seonglae Cho

seonglae

11 11 61

https://www.seongland.com

AI & ML interests

NLP, Humanoid, AGI

Recent Activity

published a Space about 2 hours ago

seonglae/PaaT

published a Space about 2 hours ago

seonglae/AgentStateGraph

published a Space about 2 hours ago

seonglae/AgentRoom

View all activity

Organizations

seonglae 's Spaces 11

AgentRoom

🏠

Watch two AI agents code together in a shared workspace

PaaT: Probe as a Tool for Proprioceptive Language Agents

🔀

Watch a model self‑assess risk and decide to proceed or stop

Automata from Agent Traces

🔁

Explore interactive finite‑state automata from LLM agent traces

Single-Token Features

🪙

Are single-token SAE features causally necessary?

OptimismBench

🎲

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

🧭

Steer text generation by clicking transformer layers

Control Reinforcement Learning

🎛

Explore LLM token decisions with feature‑driven visualizations

Seonglae Cho

AI & ML interests

Recent Activity

Organizations

seonglae 's Spaces 11 Sort: Recently updated

AgentRoom

PaaT: Probe as a Tool for Proprioceptive Language Agents

Automata from Agent Traces

Single-Token Features

OptimismBench

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

Control Reinforcement Learning

Confidence Manifold

Agent State Graph — Dashboard

Yokhal

Resrer Demo

seonglae 's Spaces 11