© 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. 2814
    Prev
    Next
    INDEX
    Explanations

    direct quotations indicated by quotation marks

    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
     protective
    -0.60
     booster
    -0.60
     listed
    -0.59
     tracker
    -0.58
     detail
    -0.58
     quir
    -0.57
     trove
    -0.56
     reserve
    -0.56
    leck
    -0.55
     guard
    -0.55
    POSITIVE LOGITS
    Our
    0.88
    We
    0.86
    Obviously
    0.83
    Tonight
    0.77
    This
    0.76
    Either
    0.76
    Right
    0.76
    Today
    0.75
    They
    0.72
    Whenever
    0.71
    Activations Density 0.065%

    No Known Activations