© 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. 2807
    Prev
    Next
    INDEX
    Explanations

    numerical values and percentages related to sales and performance metrics

    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
    bys
    -0.86
    atel
    -0.82
    itals
    -0.80
    alls
    -0.79
    idi
    -0.79
    burgh
    -0.78
    keyes
    -0.78
    loo
    -0.77
    kies
    -0.77
    atin
    -0.75
    POSITIVE LOGITS
     figure
    0.85
     renaissance
    0.77
     rarity
    0.76
     Renaissance
    0.73
    versive
    0.72
     correction
    0.71
     deviation
    0.71
     rejection
    0.70
     transformation
    0.69
     proportion
    0.68
    Activations Density 0.048%

    No Known Activations