© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 3157
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Susan."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    ARDIS
    -0.89
    icas
    -0.82
    astical
    -0.75
    eln
    -0.72
    Downloadha
    -0.71
    ierrez
    -0.70
    itars
    -0.69
    ensis
    -0.69
    ELS
    -0.68
    eware
    -0.67
    POSITIVE LOGITS
     prow
    0.65
     disrupt
    0.63
    clips
    0.62
     McF
    0.61
    heid
    0.61
     downed
    0.61
     Loving
    0.61
    wick
    0.60
    haus
    0.60
    WER
    0.60
    Activations Density 0.014%

    No Known Activations