© 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. 3187
    Prev
    Next
    INDEX
    Explanations

    queries about location or direction

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    dayName
    -0.72
    Operation
    -0.71
    CRIP
    -0.71
    ullivan
    -0.70
    UNE
    -0.67
    SW
    -0.65
    DEF
    -0.64
    Marginal
    -0.63
    RON
    -0.63
    EXP
    -0.61
    POSITIVE LOGITS
     else
    0.90
    ver
    0.85
    'd
    0.69
    else
    0.68
    abouts
    0.66
    upon
    0.66
     bios
    0.65
    as
    0.64
    chu
    0.63
     accumulated
    0.61
    Activations Density 0.044%

    No Known Activations