Inseq

AI & ML interests

Interpretability for Generative Language Models 🔎 🐛

Recent Activity

nfel  authored a paper 5 days ago

Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework

nfel  authored a paper 26 days ago

Truth or Twist? Optimal Model Selection for Reliable Label Flipping Evaluation in LLM-based Counterfactuals

nfel  authored a paper 26 days ago

Through a Compressed Lens: Investigating the Impact of Quantization on LLM Explainability and Interpretability

View all activity

Team members 3