all AI news
Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms
March 27, 2024, 4:42 a.m. | Michael Hanna, Sandro Pezzelle, Yonatan Belinkov
cs.LG updates on arXiv.org arxiv.org
Abstract: Many recent language model (LM) interpretability studies have adopted the circuits framework, which aims to find the minimal computational subgraph, or circuit, that explains LM behavior on a given task. Most studies determine which edges belong in a LM's circuit by performing causal interventions on each edge independently, but this scales poorly with model size. Edge attribution patching (EAP), gradient-based approximation to interventions, has emerged as a scalable but imperfect solution to this problem. In …
abstract arxiv behavior beyond causal circuits computational cs.cl cs.lg framework interpretability language language model studies type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US