© 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. 503
    Prev
    Next
    INDEX
    Explanations

    phrases that refer to generalizations or concepts applicable at any time or moment

    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
     Sod
    -0.71
     homophobia
    -0.70
     unic
    -0.67
     hijacked
    -0.63
     insepar
    -0.62
     blacklist
    -0.62
    copy
    -0.62
     motorcycles
    -0.61
    emia
    -0.60
    edom
    -0.60
    POSITIVE LOGITS
    ahime
    0.79
    ":["
    0.71
    =~
    0.70
    point
    0.67
    EStream
    0.66
    rate
    0.65
    Point
    0.64
    alyst
    0.64
     Turns
    0.63
     jun
    0.62
    Activations Density 0.015%

    No Known Activations