© 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. 1679
    Prev
    Next
    INDEX
    Explanations

    indicators of formal or structured content, possibly related to reports or documentation

    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
    Problem
    -0.76
    NG
    -0.75
    patch
    -0.67
     Gins
    -0.62
     brow
    -0.62
    hips
    -0.61
    Linux
    -0.60
     CK
    -0.60
     Zip
    -0.59
     Thrones
    -0.59
    POSITIVE LOGITS
    aced
    0.81
    allery
    0.79
    neapolis
    0.75
    nton
    0.74
    endants
    0.74
    sted
    0.70
    chen
    0.67
    iami
    0.66
    acements
    0.66
    endant
    0.65
    Activations Density 0.060%

    No Known Activations