🪴

      • ACID
      • AWS Notes
      • bit hacks
      • CAP Theorem
      • code snippets
      • cool tools
      • courses
      • embeddings
      • for the love of browser
      • home lab
      • idea list
      • integral images
      • internet gems
      • L1 and L2 regularization
      • language models
      • learning computers
      • library
      • linus lee talk (2023-10-18)
      • luck surfaces
      • manifesto
      • mechanistic interpretability
      • ML Links
      • MLIB practice problems
      • Notes
      • open-Source LLMs
      • podcasts
      • probabilistic counting
      • Redis
      • sci-fi books
      • setting up a mac
      • singular value decomposition
      • spaced repetition
      • ssh scripts
      • startups to follow
      • system design interviews
      • systems whitepapers
      • tensor puzzles
      • textbooks
      • topics to explore
      • transformers
      • two cultures of statistical modeling
      • vimGPT
        • hiring yap
        • tech without industry
        • Yaps
    Home

    ❯

    Notes

    ❯

    mechanistic interpretability

    mechanistic interpretability

    Oct 27, 20231 min read

    • seed
    • https://transformer-circuits.pub/2023/monosemantic-features/index.html
    • https://transformer-circuits.pub/
    • https://distill.pub/
    • https://www.neelnanda.io/mechanistic-interpretability

    Graph View

    Created with Quartz v4.4.0 © 2025

    • GitHub
    • Discord Community