11 citations · 20 across the 10 of their papers we have counts for
4 papers · 1 filter
Slaying the Hydra: Interaction-Aware Circuit Discovery in Language Models
Sankaran Vaidyanathan, Rafal Urbaniak, Emily Bunnapradist +2
Localizing behavior to individual components of a language model is a central goal of mechanistic interpretability. However, scoring components one at a time misses context-depende…
The Curse of Multiple Mediators: Hidden Interaction Effects in Activation Patching
Sankaran Vaidyanathan, David Arbour, Aaron Mueller +2
Activation patching is the primary tool in mechanistic interpretability. It attributes causal responsibility for a model behavior to each of its individual components by estimating…
Adaptive Circuit Behavior and Generalization in Mechanistic Interpretability
Jatin Nainani, Sankaran Vaidyanathan, AJ Yeung +2
Mechanistic interpretability aims to understand the inner workings of large neural networks by identifying circuits, or minimal subgraphs within the model that implement algorithms…
Hypergraph Clustering: A Modularity Maximization Approach
Tarun Kumar, Sankaran Vaidyanathan, Harini Ananthapadmanabhan +2
Clustering on hypergraphs has been garnering increased attention with potential applications in network analysis, VLSI design and computer vision, among others. In this work, we ge…