© 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
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1336
    Prev
    Next
    INDEX
    Explanations

    content related to quantitative assessments and labeling

    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
     inward
    -0.68
     implied
    -0.60
     diseng
    -0.59
     outsiders
    -0.56
     cooking
    -0.55
     vegetable
    -0.55
     entertain
    -0.54
     dimensional
    -0.54
     clothes
    -0.54
     err
    -0.53
    POSITIVE LOGITS
    multiple
    1.06
    many
    0.97
    Multiple
    0.94
    ワン
    0.91
    Four
    0.86
     multiple
    0.85
    sever
    0.83
    umerous
    0.82
     Multiple
    0.82
    Five
    0.82
    Activations Density 2.175%

    No Known Activations