Not all language model features are one-dimensionally linear

{
  "doi": null,
  "year": 2024,
  "title": "Not all language model features are one-dimensionally linear",
  "venue": null,
  "authors": [
    "Joshua Engels",
    "Eric J Michaud",
    "Isaac Liao",
    "Wes Gurnee",
    "Max Tegmark"
  ],
  "arxiv_id": "2405.14860",
  "s2_paper_id": null,
  "ingest_status": "referenced-only"
}