Seonglae Cho

seonglae-holistic

·

https://huggingface.co/seonglae

AI & ML interests

None yet

Recent Activity

upvoted a paper 8 days ago

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

upvoted a paper 8 days ago

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

upvoted a paper 11 days ago

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

View all activity

Organizations

upvoted 2 papers 8 days ago

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

Paper • 2602.10437 • Published Feb 12 • 2

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

Paper • 2607.26981 • Published 10 days ago • 2

upvoted a paper 11 days ago

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

Paper • 2607.20596 • Published 17 days ago • 2

liked a dataset 3 months ago

EleutherAI/hendrycks_math

Viewer • Updated Jan 12, 2025 • 12.5k • 157k • 108

liked a Space 3 months ago

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

Steer language model output by clicking visual layers

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

liked 2 models 6 months ago

google/gemma-scope-2

Updated Dec 19, 2025 • 90

nvidia/personaplex-7b-v1

Audio-to-Audio • 8B • Updated Mar 2 • 201k • • 2.65k

liked 2 models 7 months ago

google/embeddinggemma-300m

Sentence Similarity • 0.3B • Updated Sep 25, 2025 • 2.07M • • 1.83k

google/translategemma-4b-it

Image-Text-to-Text • 5B • Updated Jan 28 • 131k • 818

liked a Space 7 months ago

MTEB Leaderboard

Embedding Leaderboard

liked a dataset 7 months ago

nvidia/PhysicalAI-SimReady-Warehouse-01

Viewer • Updated Dec 3, 2025 • 753 • 8.05k • 49

liked a model 7 months ago

black-forest-labs/FLUX.2-dev

Image-to-Image • 32B • Updated Feb 17 • 941k • • 2k

liked a Space 8 months ago

Bringing paper to life: A modern template for scientific writing

Explore an interactive galaxy visualization of scientific article

updated a Space 11 months ago

LibVulnWatch

Vulnerability scores for AI libraries (ACL '25, ICML '25)

updated a Space about 1 year ago

LibVulnWatch

Vulnerability scores for AI libraries (ACL '25, ICML '25)

liked a Space about 1 year ago

LibVulnWatch

Vulnerability scores for AI libraries (ACL '25, ICML '25)

updated a Space about 1 year ago

LibVulnWatch

Vulnerability scores for AI libraries (ACL '25, ICML '25)

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

New activity in holistic-ai/LibVulnWatch about 1 year ago

refactor: update table columns

#1 opened about 1 year ago by

seonglae-holistic