© 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. 2186
    Prev
    Next
    INDEX
    Explanations

    punctuation and contextually relevant phrases indicative of programming or data-processing tasks

    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
    perse
    -0.65
    */(
    -0.64
    orie
    -0.64
    heid
    -0.64
     Advocate
    -0.61
     Activities
    -0.61
    ��
    -0.59
     Employees
    -0.58
    ITNESS
    -0.57
    Action
    -0.56
    POSITIVE LOGITS
    so
    0.79
    stem
    0.73
     eg
    0.69
     ensuring
    0.67
     eliminating
    0.66
    heric
    0.65
     thus
    0.63
     guaranteeing
    0.63
     enabling
    0.62
     preventing
    0.62
    Activations Density 0.270%

    No Known Activations