Aashiq Muhamed

aashiqmuhamed's activity

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

commented a paper 4 days ago

Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs

Paper • 2505.20254 • Published 4 days ago • 5 •

1

commented 2 papers about 2 months ago

CoRAG: Collaborative Retrieval-Augmented Generation

Paper • 2504.01883 • Published Apr 2 • 10 •

2

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

Paper • 2504.08192 • Published Apr 11 • 4 •

2

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

commented a paper 11 months ago

Grass: Compute Efficient Low-Memory LLM Training with Structured Sparse Gradients

Paper • 2406.17660 • Published Jun 25, 2024 • 5 •

3