© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 481
    Prev
    Next
    INDEX
    Explanations

    specific data points and formats related to release dates and durations

    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
    abella
    -0.75
    ucket
    -0.70
    FTWARE
    -0.69
    che
    -0.66
    light
    -0.65
    claw
    -0.64
    LOG
    -0.63
    icz
    -0.63
    water
    -0.63
    elo
    -0.62
    POSITIVE LOGITS
     Ancients
    0.78
     Creator
    0.71
     Samar
    0.68
     Templ
    0.65
     Kant
    0.62
    Jam
    0.62
     Orders
    0.61
     Moder
    0.60
     Seller
    0.60
    itors
    0.60
    Activations Density 0.159%

    No Known Activations