© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 2800
    Prev
    Next
    INDEX
    Explanations

    phrases that repeatedly reference the word "of," indicating a focus on relationships or quantities associated with items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hess
    -0.70
    oker
    -0.66
     Sold
    -0.63
    spoken
    -0.61
    chenko
    -0.61
    former
    -0.61
     reigning
    -0.61
     jailed
    -0.60
    rigan
    -0.60
     Held
    -0.59
    POSITIVE LOGITS
    �
    0.72
    aper
    0.67
    Leaks
    0.63
     Tet
    0.62
    ッド
    0.61
    yp
    0.61
     pH
    0.60
     Clubs
    0.59
     pivot
    0.59
     Arrows
    0.59
    Activations Density 0.038%

    No Known Activations