1 citations · 1 across the 11 of their papers we have counts for
Showing 2025Show all
3 papers · 1 filter
cs.CL2025
CorrSteer: Generation-Time LLM Steering via Correlated Sparse Autoencoder Features
Seonglae Cho, Zekun Wu, Adriano Koshiyama
Sparse Autoencoders (SAEs) can extract interpretable features from large language models (LLMs) without supervision. However, their effectiveness in downstream steering tasks is li…
cs.CR2025
LibVulnWatch: A Deep Assessment Agent System and Leaderboard for Uncovering Hidden Vulnerabilities in Open-Source AI Libraries
Zekun Wu, Seonglae Cho, Umar Mohammed +7
Open-source AI libraries are foundational to modern AI systems, yet they present significant, underexamined risks spanning security, licensing, maintenance, supply chain integrity,…
cs.LG2025
FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Dataset Dependencies
Seonglae Cho, Harryn Oh, Donghyun Lee +3
Sparse Autoencoders (SAEs) have emerged as a promising solution for decomposing large language model representations into interpretable features. However, Paulo and Belrose (2025)…