{
  "id": "2405.15071",
  "title": "Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization",
  "authors": "Boshi Wang, Xiang Yue, Yu Su, Huan Sun",
  "first_public": "2024-05-23",
  "venue": "arXiv",
  "arxiv": "2405.15071",
  "paper_url": "https://arxiv.org/abs/2405.15071",
  "lens": [
    "analysis"
  ],
  "representation": [
    "hidden-state"
  ],
  "computation": [
    "depth-wise"
  ],
  "training": [
    "analysis-only"
  ],
  "questions": [
    "interpretability",
    "generalization"
  ],
  "evidence": [
    "empirical",
    "mechanistic"
  ],
  "modality": [
    "symbolic"
  ],
  "summary": "Mechanistically studies transformers that learn implicit reasoning after grokking, focusing on how internal algorithms support out-of-distribution generalization.",
  "provenance": "Awesome-Latent-CoT",
  "author_names": [
    "Boshi Wang",
    "Xiang Yue",
    "Yu Su",
    "Huan Sun"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2405.15071/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2405-15071",
  "citation_date": "2024-05-23",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2405.15071/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2405.15071/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2405.15071/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2405.15071/citation.csl.json"
}