Seonglae Cho

seonglae-holistic's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 2 days ago

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

Paper • 2602.10437 • Published Feb 12 • 2

upvoted a paper 3 days ago

OptimismBench: Forecasting Bias and the Alignment Effect in Language Model Judgment

Paper • 2607.26981 • Published 4 days ago • 2

upvoted a paper 5 days ago

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

Paper • 2607.20596 • Published 11 days ago • 2

upvoted a paper 6 months ago

CorrSteer: Steering Improves Task Performance and Safety in LLMs through Correlation-based Sparse Autoencoder Feature Selection

Paper • 2508.12535 • Published Aug 18, 2025 • 2

upvoted a paper about 1 year ago

FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Dataset Dependencies

Paper • 2506.17673 • Published Jun 21, 2025 • 7