Interpretability features converge across different model architectures, revealing structural similarities.

{
  "doc": "/Users/antonborzov/Documents/Research.nosync/notes/RESEARCH-VECTORS.md",
  "claim": "Interpretability features converge across different model architectures, revealing structural similarities.",
  "vector": "convergent-representations",
  "section": "6. Convergent Representations",
  "extracted_at": 1778899419,
  "extracted_by": "haiku-4-5",
  "supporting_refs": [
    "interpretability research"
  ]
}