© 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. 3122
    Prev
    Next
    INDEX
    Explanations

    special characters or formatting elements in text

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    enegger
    -0.79
    NK
    -0.71
    TL
    -0.71
     Malk
    -0.70
    oos
    -0.68
    ignty
    -0.67
    liner
    -0.66
     selves
    -0.65
    WER
    -0.64
    oon
    -0.63
    POSITIVE LOGITS
    isite
    0.78
     sustained
    0.67
    asus
    0.65
    orable
    0.65
    classic
    0.65
     Conrad
    0.64
     overnight
    0.64
    uador
    0.64
     prolonged
    0.63
    olulu
    0.63
    Activations Density 1.771%

    No Known Activations