Interpretability

Interpretability Can Be Actionable
Old Habits Die Hard: How Conversational History Geometrically Traps LLMs
Position: Don't Just "Fix it in Post": A Science of AI Must Study Training Dynamics
Query Circuits: Explaining How Language Models Answer User Prompts
Towards Understanding Subliminal Learning: When and How Hidden Biases Transfer
Same Answer, Different Representations: Hidden Instability in VLMs
The Hitchhiker's Guide to Actionable Interpretability
Automated Interpretability-Driven Model Auditing and Control: A Research Agenda
Quantifying the Effect of Test Set Contamination on Generative Evaluations
Context Matters: Analyzing the Generalizability of Linear Probing and Steering Across Diverse Scenarios