🏗️ Building on HF

Seonglae Cho

seonglae

11 11 61

https://www.seongland.com

seonglaeC
seonglae

AI & ML interests

NLP, Humanoid, AGI

Recent Activity

updated a Space 3 days ago

seonglae/ConfidenceManifold

updated a Space 3 days ago

seonglae/ControlRL

updated a Space 3 days ago

seonglae/CorrSteer

View all activity

Organizations

seonglae 's Spaces 11

PaaT: Probe as a Tool for Proprioceptive Language Agents

🔀

Visualize self‑monitoring probes for AI model safety

Automata from Agent Traces

🔁

Explore interactive automata from LLM agent traces

AgentRoom

🏠

Explore a live demo of coordinated AI coding agents

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

Single-Token Features

🪙

Are single-token SAE features causally necessary?

Seonglae Cho

AI & ML interests

Recent Activity

Organizations

seonglae 's Spaces 11 Sort: Recently updated

PaaT: Probe as a Tool for Proprioceptive Language Agents

Automata from Agent Traces

AgentRoom

Confidence Manifold

Control Reinforcement Learning

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

Single-Token Features

OptimismBench

Agent State Graph — Dashboard

Yokhal

Resrer Demo

seonglae 's Spaces 11