© 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. 2717
    Prev
    Next
    INDEX
    Explanations

    references to population statistics and numbers

    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
     Cosponsors
    -0.69
     Responsibility
    -0.66
    hurst
    -0.65
     assurance
    -0.63
     RELEASE
    -0.62
    teness
    -0.61
    Loading
    -0.61
    ILA
    -0.61
    STRUCT
    -0.61
    Trend
    -0.60
    POSITIVE LOGITS
    erers
    0.81
     people
    0.74
     somebody
    0.65
     someone
    0.64
    unci
    0.63
    ients
    0.62
     pilots
    0.61
    itors
    0.61
     passengers
    0.61
     adherents
    0.61
    Activations Density 0.088%

    No Known Activations