Harry Mayne

HarryMayne's activity

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

upvoted a paper 10 days ago

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

Paper • 2411.08790 • Published 16 days ago • 8

upvoted a paper 16 days ago

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

Paper • 2411.06424 • Published 19 days ago • 5

upvoted a paper 7 months ago

ReFT: Representation Finetuning for Language Models

Paper • 2404.03592 • Published Apr 4 • 90