Heejune Sheen

[Zhuoran Yang @zhuoran_yang]

🚀 We're excited to share our paper, "Taming Polysemanticity in LLMs," which introduces Group Bias Adaptation (GBA)—the FIRST Sparse Autoencoder (SAE) training method with a provable guarantee for untangling monosemantic concepts!

📄 Paper: https://t.co/CzzEfaTWIg
🌐 Website: https://t.co/J2tCfJx3l2
🎯 Demo (Layer 26 of Qwen 2.5B-Base): https://t.co/4Dr1XjKoXU

Joint work with @siyuc3141, @HeejuneSheen, Xuyuan Xiong, and @0920wth

[Zhuoran Yang @zhuoran_yang]

[New Paper on In-Context Learning]
Title: Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers
Joint work with @siyuc3141 @HeejuneSheen @0920wth
Link: https://t.co/BZPBnVmq6b