Harry Mayne

HarryMayne's activity

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

upvoted a paper 6 days ago

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

Paper • 2411.08790 • Published 12 days ago • 8

authored a paper 10 days ago

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

Paper • 2411.08790 • Published 12 days ago • 8

upvoted a paper 12 days ago

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

Paper • 2411.06424 • Published 16 days ago • 5

liked a dataset about 2 months ago

ambean/lingOly

Viewer • Updated Jun 11 • 90 • 123 • 7

liked a dataset 4 months ago

monology/pile-uncopyrighted

Viewer • Updated Aug 31, 2023 • 1.25M • 125k • 112

liked a model 6 months ago

meta-llama/Llama-2-7b

Text Generation • Updated Apr 17 • 4.16k

liked a dataset 6 months ago

Anthropic/hh-rlhf

Viewer • Updated May 26, 2023 • 169k • 9.37k • 1.21k

upvoted a paper 7 months ago

ReFT: Representation Finetuning for Language Models

Paper • 2404.03592 • Published Apr 4 • 90

liked a model 7 months ago

meta-llama/Meta-Llama-3-8B

Text Generation • Updated Sep 27 • 683k • 5.84k

liked 3 datasets 8 months ago

uonlp/CulturaX

Viewer • Updated Jul 23 • 7.18B • 9.51k • 475

Skylion007/openwebtext

Updated May 17 • 40.7k • 372

EleutherAI/pile

Updated May 3, 2023 • 1.21k • 401

liked a model 10 months ago

snorkelai/Snorkel-Mistral-PairRM-DPO

Text Generation • Updated May 13 • 810 • 106

liked a Space about 1 year ago

Running on Zero

4.71k

👁

IllusionDiffusion

Generate stunning high quality illusion artwork