Mib: A mechanistic interpretability benchmark

{
  "doi": null,
  "year": 2025,
  "title": "Mib: A mechanistic interpretability benchmark",
  "venue": "arXiv",
  "authors": [
    "Aaron Mueller",
    "Atticus Geiger",
    "Sarah Wiegreffe",
    "Dana Arad",
    "Iván Arcuschin",
    "Adam Belfki",
    "Yik Siu Chan",
    "Jaden Fiotto-Kaufman",
    "Tal Haklay",
    "Michael Hanna",
    "Jing Huang",
    "Rohan Gupta",
    "Yaniv Nikankin",
    "Hadas Orgad",
    "Nikhil Prakash",
    "Anja Reusch",
    "Aruna Sankaranarayanan",
    "Shun Shao",
    "Alessandro Stolfo",
    "Martin Tutek",
    "Amir Zur",
    "David Bau",
    "Yonatan Belinkov"
  ],
  "arxiv_id": "2504.13151",
  "s2_paper_id": null,
  "ingest_status": "referenced-only"
}