© 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. 2867
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "When" that indicate various scenarios or memories

    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
    fail
    -0.68
    AMS
    -0.64
    venants
    -0.63
    hibit
    -0.63
    ilver
    -0.62
     subtitle
    -0.61
    ttle
    -0.61
    dule
    -0.61
    cko
    -0.61
    wcsstore
    -0.60
    POSITIVE LOGITS
     Sina
    0.75
     Sergey
    0.73
     Jean
    0.69
     Jonathan
    0.69
     Anton
    0.68
     David
    0.68
     Stephan
    0.67
     Yose
    0.67
     Elena
    0.67
     Vladimir
    0.66
    Activations Density 0.029%

    No Known Activations