© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1318
    Prev
    Next
    INDEX
    Explanations

    occurrences of parentheses in dependencies or function calls

    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
     bids
    -0.76
     IA
    -0.65
     bidding
    -0.62
     Dawn
    -0.62
     plus
    -0.62
     MS
    -0.60
     Britann
    -0.60
     Rating
    -0.58
    enegger
    -0.58
    ALLY
    -0.57
    POSITIVE LOGITS
    hab
    0.90
    power
    0.88
    stru
    0.83
    init
    0.80
    parts
    0.80
    function
    0.79
    ufact
    0.79
    parse
    0.78
    cur
    0.77
    iHUD
    0.77
    Activations Density 0.022%

    No Known Activations