Mor Geva

mega's activity

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

authored a paper about 1 month ago

Universal Jailbreak Suffixes Are Strong Attention Hijackers

Paper • 2506.12880 • Published Jun 15 • 5

authored a paper about 2 months ago

Decomposing MLP Activations into Interpretable Features via Semi-Nonnegative Matrix Factorization

Paper • 2506.10920 • Published Jun 12 • 6

authored 2 papers 6 months ago

Open Problems in Mechanistic Interpretability

Paper • 2501.16496 • Published Jan 27 • 19

Enhancing Automated Interpretability with Output-Centric Feature Descriptions

Paper • 2501.08319 • Published Jan 14 • 11

authored a paper 12 months ago

CoverBench: A Challenging Benchmark for Complex Claim Verification

Paper • 2408.03325 • Published Aug 6, 2024 • 15

upvoted a paper 12 months ago

Knesset-DictaBERT: A Hebrew Language Model for Parliamentary Proceedings

Paper • 2407.20581 • Published Jul 30, 2024 • 25

authored 2 papers about 1 year ago

Evaluating the Ripple Effects of Knowledge Editing in Language Models

Paper • 2307.12976 • Published Jul 24, 2023 • 12

From Loops to Oops: Fallback Behaviors of Language Models Under Uncertainty

Paper • 2407.06071 • Published Jul 8, 2024 • 7

upvoted a collection about 1 year ago

🔍 Interpretability & Analysis of LMs

Collection

Outstanding research in LM interpretability and evaluation, summarized • 123 items • Updated 4 days ago • 109

authored a paper about 1 year ago

Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces

Paper • 2406.11614 • Published Jun 17, 2024 • 5

commented a paper about 1 year ago

Estimating Knowledge in Large Language Models Without Generating a Single Token

Paper • 2406.12673 • Published Jun 18, 2024 • 8 •

1

authored 3 papers over 1 year ago

Do Large Language Models Latently Perform Multi-Hop Reasoning?

Paper • 2402.16837 • Published Feb 26, 2024 • 30

Patchscope: A Unifying Framework for Inspecting Hidden Representations of Language Models

Paper • 2401.06102 • Published Jan 11, 2024 • 23

Narrowing the Knowledge Evaluation Gap: Open-Domain Question Answering with Multi-Granularity Answers

Paper • 2401.04695 • Published Jan 9, 2024 • 13

authored a paper almost 2 years ago

In-Context Learning Creates Task Vectors

Paper • 2310.15916 • Published Oct 24, 2023 • 43

authored a paper about 2 years ago

The Hidden Language of Diffusion Models

Paper • 2306.00966 • Published Jun 1, 2023 • 5