© 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. 631
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of people and characters

    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
     planners
    -0.72
     Leilan
    -0.62
     decor
    -0.57
     Koreans
    -0.57
     Legislation
    -0.56
     Russians
    -0.56
     planner
    -0.56
     Contracts
    -0.55
     liberals
    -0.55
     bureaucrats
    -0.55
    POSITIVE LOGITS
    steen
    0.76
    enegger
    0.73
    emonic
    0.73
    acci
    0.72
    ideon
    0.71
    lopp
    0.70
    estern
    0.70
    andowski
    0.70
    buquerque
    0.70
    eeper
    0.69
    Activations Density 0.534%

    No Known Activations