© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 2570
    Prev
    Next
    INDEX
    Explanations

    roles and job titles within various professional contexts

    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
     reminder
    -0.68
    ICLE
    -0.62
    Attempts
    -0.61
    Mit
    -0.60
     regretted
    -0.60
     Discrimination
    -0.59
     Cells
    -0.59
     Compared
    -0.59
     ton
    -0.58
     Activ
    -0.58
    POSITIVE LOGITS
     aboard
    0.73
    luaj
    0.71
     onboard
    0.69
    ivities
    0.66
    leans
    0.65
    resp
    0.64
     upstairs
    0.63
     Bundy
    0.62
    blance
    0.61
    olor
    0.61
    Activations Density 0.187%

    No Known Activations