David Newman

darthhexx's activity

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

upvoted a paper 10 days ago

I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders

Paper • 2503.18878 • Published 12 days ago • 110

upvoted 2 papers about 1 month ago

LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers

Paper • 2502.15007 • Published Feb 20 • 169

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

Paper • 2502.14739 • Published Feb 20 • 99

upvoted a collection 10 months ago

DeepSeekCoder-V2

Collection

6 items • Updated Sep 5, 2024 • 92

upvoted 2 papers 10 months ago

Depth Anything V2

Paper • 2406.09414 • Published Jun 13, 2024 • 102

An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels

Paper • 2406.09415 • Published Jun 13, 2024 • 51

upvoted a paper over 1 year ago

Steering Llama 2 via Contrastive Activation Addition

Paper • 2312.06681 • Published Dec 9, 2023 • 15