© 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
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1128
    Prev
    Next
    INDEX
    Explanations

    references to the quality and sustainability of publications

    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
     overhe
    -0.56
    bec
    -0.56
    adoes
    -0.55
     never
    -0.55
     eventually
    -0.54
    kept
    -0.54
     doubted
    -0.54
     ultimately
    -0.53
     otherwise
    -0.53
     needless
    -0.53
    POSITIVE LOGITS
    覚醒
    0.79
    hyde
    0.74
    ologue
    0.72
    anguage
    0.70
    代
    0.69
    onym
    0.67
    子
    0.64
    tainment
    0.63
    orage
    0.63
    roma
    0.62
    Activations Density 0.021%

    No Known Activations