© 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. 2204
    Prev
    Next
    INDEX
    Explanations

    instances of the word "first"

    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
    ones
    -0.68
    quet
    -0.66
    oyer
    -0.66
    aturday
    -0.63
    Else
    -0.63
    aro
    -0.62
    aval
    -0.61
    entimes
    -0.60
    HAM
    -0.59
    anges
    -0.59
    POSITIVE LOGITS
    fell
    0.69
    enda
    0.66
     started
    0.59
     began
    0.59
    ensis
    0.57
    clip
    0.57
     glim
    0.57
     TAG
    0.56
    ⓘ
    0.56
    iton
    0.56
    Activations Density 0.059%

    No Known Activations