Aashiq Muhamed

aashiqmuhamed's activity

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

authored 3 papers 4 days ago

SAEs $\textit{Can}$ Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs

Paper • 2504.08192 • Published Apr 11 • 4

CoRAG: Collaborative Retrieval-Augmented Generation

Paper • 2504.01883 • Published Apr 2 • 10

Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs

Paper • 2505.20254 • Published 4 days ago • 5

upvoted a paper 4 days ago

Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs

Paper • 2505.20254 • Published 4 days ago • 5

commented a paper 4 days ago

Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs

Paper • 2505.20254 • Published 4 days ago • 5 •

1

liked a model 24 days ago

deepseek-ai/DeepSeek-Prover-V2-7B

Updated about 1 month ago • 44.8k • 108

liked a dataset about 1 month ago

Anthropic/values-in-the-wild

Viewer • Updated Apr 28 • 6.91k • 1.24k • 130

liked a Space about 1 month ago

Running

2.63k

2.63k

The Ultra-Scale Playbook

🌌

The ultimate guide to training LLM on large GPU Clusters

upvoted a paper about 2 months ago

CoRAG: Collaborative Retrieval-Augmented Generation

Paper • 2504.01883 • Published Apr 2 • 10

commented a paper about 2 months ago

CoRAG: Collaborative Retrieval-Augmented Generation

Paper • 2504.01883 • Published Apr 2 • 10 •

2

upvoted a paper about 2 months ago

SAEs Can Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs

Paper • 2504.08192 • Published Apr 11 • 4

commented a paper about 2 months ago

SAEs $\textit{Can}$ Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs

Paper • 2504.08192 • Published Apr 11 • 4 •

2

updated 2 models 2 months ago

aashiqmuhamed/gemma-2b-muse-books-target

Text Generation • Updated Mar 19 • 10

aashiqmuhamed/gemma-2b-muse-news-target

Text Generation • Updated Mar 19 • 10

published 2 models 2 months ago

aashiqmuhamed/gemma-2b-muse-books-target

Text Generation • Updated Mar 19 • 10

aashiqmuhamed/gemma-2b-muse-news-target

Text Generation • Updated Mar 19 • 10

authored a paper 7 months ago

Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models

Paper • 2411.00743 • Published Nov 1, 2024 • 7

upvoted a paper 7 months ago

Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models

Paper • 2411.00743 • Published Nov 1, 2024 • 7

commented a paper 7 months ago

Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models

Paper • 2411.00743 • Published Nov 1, 2024 • 7 •

2

liked a dataset 8 months ago

facebook/Self-taught-evaluator-DPO-data

Viewer • Updated Feb 7 • 57.5k • 33 • 35