© 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
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 2370
    Prev
    Next
    INDEX
    Explanations

    the repeated use of the word "Another" to indicate additional instances or examples

    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
    rued
    -0.86
    verage
    -0.72
    enos
    -0.70
    annels
    -0.69
    tails
    -0.69
    nces
    -0.68
    ravis
    -0.68
    UTERS
    -0.67
    agues
    -0.67
    rils
    -0.66
    POSITIVE LOGITS
     plot
    0.70
    izable
    0.63
     name
    0.63
     laureate
    0.61
     mosaic
    0.61
     reason
    0.61
     supplier
    0.59
     youngster
    0.59
     lawyer
    0.59
    osen
    0.59
    Activations Density 0.053%

    No Known Activations