YY

yy0514's activity

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

commented 2 papers 10 months ago

Can sparse autoencoders be used to decompose and interpret steering vectors?

Paper • 2411.08790 • Published Nov 13, 2024 • 8 •

2

Ablation is Not Enough to Emulate DPO: How Neuron Dynamics Drive Toxicity Reduction

Paper • 2411.06424 • Published Nov 10, 2024 • 5 •

2

commented a paper about 1 year ago

Fine-tuning Large Language Models with Human-inspired Learning Strategies in Medical Question Answering

Paper • 2408.07888 • Published Aug 15, 2024 • 13 •

2