© 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. 1573
    Prev
    Next
    INDEX
    Explanations

    references to new or upcoming releases and products

    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
    Els
    -0.68
    imentary
    -0.68
    imir
    -0.67
    anish
    -0.67
    yip
    -0.66
    idth
    -0.64
    ASH
    -0.61
    ashes
    -0.60
    agues
    -0.60
    agg
    -0.60
    POSITIVE LOGITS
    vg
    0.71
    wine
    0.67
    ffiti
    0.64
     handwritten
    0.64
    pha
    0.63
     tremend
    0.61
     fax
    0.61
     pamph
    0.61
     sax
    0.59
     Suite
    0.59
    Activations Density 0.058%

    No Known Activations