© 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. 2058
    Prev
    Next
    INDEX
    Explanations

    references to the color yellow

    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
     Flavoring
    -0.77
    lihood
    -0.68
     Conserv
    -0.68
    awaru
    -0.64
    Attributes
    -0.63
    itar
    -0.60
    ============
    -0.59
    ................................................................
    -0.58
     ..............
    -0.57
     Ecology
    -0.57
    POSITIVE LOGITS
    eger
    0.82
    prints
    0.78
    bill
    0.76
     Schwarz
    0.65
     blur
    0.65
     sticky
    0.65
    stone
    0.61
     railing
    0.60
    critical
    0.60
     pads
    0.60
    Activations Density 0.046%

    No Known Activations