Alex Xi's Notes

Tag: interpretability

8 items with this tag.

  • Jul 06, 2026

    tweet-transformer-circuits-mental-model

    • transformers
    • interpretability
    • circuits
  • Jul 06, 2026

    tweet-generative-meta-model-activations

    • diffusion
    • activations
    • interpretability
    • meta-learning
    • stanford
  • Jul 06, 2026

    tweet-llm-invertibility

    • embeddings
    • security
    • interpretability
    • llm
    • privacy
  • Jul 06, 2026

    tweet-silico-model-debugging

    • interpretability
    • debugging
    • model-engineering
    • startup
  • Jul 06, 2026

    textual-steering-vectors-multimodal

    • interpretability
    • steering-vectors
    • multimodal
    • vision
  • Jul 06, 2026

    anthropic-emotion-concepts

    • interpretability
    • emotions
    • ai-character
    • alignment
    • anthropic
    • mechanistic-interpretability
  • Jul 06, 2026

    bytebytego-how-claude-thinks

    • interpretability
    • mechanistic-interpretability
    • claude
    • anthropic
    • features
    • polysemanticity
  • Jul 06, 2026

    mechanistic-interpretability

    • mechanistic-interpretability
    • features
    • polysemanticity
    • anthropic
    • interpretability