© 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. 1720
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating quantities or amounts

    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
    arth
    -0.69
    SourceFile
    -0.69
    artifacts
    -0.69
    chairs
    -0.68
    gallery
    -0.66
    pole
    -0.65
    Pie
    -0.61
     blight
    -0.61
    Stars
    -0.60
    letters
    -0.60
    POSITIVE LOGITS
     desired
    0.69
     normal
    0.66
    inarily
    0.65
    normal
    0.64
     necessary
    0.63
    enegger
    0.63
    ensible
    0.63
     usual
    0.63
     permissible
    0.63
     advisable
    0.62
    Activations Density 0.087%

    No Known Activations