© 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. 2072
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers or special character sequences

    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
    ework
    -0.71
    cheat
    -0.70
    older
    -0.58
    REC
    -0.58
    soDeliveryDate
    -0.57
     reassuring
    -0.57
    circle
    -0.56
     juggling
    -0.55
     explaining
    -0.55
    rule
    -0.54
    POSITIVE LOGITS
    oulos
    0.75
    pb
    0.65
    chwitz
    0.63
    gow
    0.62
     curs
    0.61
     Starts
    0.61
     McCull
    0.59
     actionGroup
    0.59
     chromosomes
    0.58
    eson
    0.58
    Activations Density 0.247%

    No Known Activations