9 5 61

Seonglae Cho

seonglae

https://www.seongland.com

AI & ML interests

NLP, Humanoid, AGI

Recent Activity

updated a dataset 5 days ago

seonglae/streamwriter-100k-edge

published a dataset 5 days ago

seonglae/streamwriter-100k-edge

updated a Space 16 days ago

seonglae/CorrSteer

View all activity

Organizations

updated a dataset 5 days ago

seonglae/streamwriter-100k-edge

Viewer • Updated 5 days ago • 74.8k • 31

published a dataset 5 days ago

seonglae/streamwriter-100k-edge

Viewer • Updated 5 days ago • 74.8k • 31

updated a Space 16 days ago

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

🧭

Steer language model output with interactive layer clicks

updated a dataset 25 days ago

seonglae/streamwriter-triplets-10k

Viewer • Updated 25 days ago • 9.99k • 32.3k

updated 2 Spaces about 1 month ago

Confidence Manifold

🧭

Control Reinforcement Learning

🎛

Explore LLM token decisions with feature‑driven visualizations

updated a dataset 2 months ago

seonglae/lc-ode1

Viewer • Updated Mar 11 • 136k • 18

published a dataset 2 months ago

seonglae/lc-ode1

Viewer • Updated Mar 11 • 136k • 18

updated a dataset 2 months ago

seonglae/math-pde

Viewer • Updated Mar 11 • 7.17k • 14

published 2 datasets 2 months ago

seonglae/math-pde

Viewer • Updated Mar 11 • 7.17k • 14

seonglae/streamwriter-triplets-10k

Viewer • Updated 25 days ago • 9.99k • 32.3k

updated a dataset 2 months ago

seonglae/streamwriter-triplets-10k-legacy

Preview • Updated Mar 5 • 25.2k

published a dataset 2 months ago

seonglae/streamwriter-triplets-10k-legacy

Preview • Updated Mar 5 • 25.2k

authored a paper 3 months ago

The Confidence Manifold: Geometric Structure of Correctness Representations in Language Models

Paper • 2602.08159 • Published Feb 8

updated a dataset 3 months ago

seonglae/streamwriter-triplets-10k-v2

Viewer • Updated Feb 28 • 28

published a dataset 3 months ago

seonglae/streamwriter-triplets-10k-v2

Viewer • Updated Feb 28 • 28

published 2 Spaces 3 months ago

Control Reinforcement Learning

🎛

Explore LLM token decisions with feature‑driven visualizations

Confidence Manifold

🧭

updated a dataset 3 months ago

seonglae/streamwriter-triplets-1k

Viewer • Updated Feb 6 • 1k • 25

published a dataset 3 months ago

seonglae/streamwriter-triplets-1k

Viewer • Updated Feb 6 • 1k • 25

Seonglae Cho

AI & ML interests

Recent Activity

Organizations

seonglae's activity

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

Confidence Manifold

Control Reinforcement Learning

Control Reinforcement Learning

Confidence Manifold