© 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. 2591
    Prev
    Next
    INDEX
    Explanations

    references to the word "on."

    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
    imilation
    -0.68
    soft
    -0.67
     groove
    -0.65
    otions
    -0.65
     halting
    -0.64
    ospace
    -0.64
    iage
    -0.64
     plea
    -0.63
     deterrent
    -0.62
    ikan
    -0.62
    POSITIVE LOGITS
     occasion
    0.82
     Saturdays
    0.81
    erous
    0.79
     Sundays
    0.78
    ENDED
    0.70
     Beir
    0.69
    twitter
    0.68
    orders
    0.68
     Fridays
    0.68
    eday
    0.68
    Activations Density 0.129%

    No Known Activations