© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1119
    Prev
    Next
    INDEX
    Explanations

    instances of the word "go" with varying contexts

    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
    atta
    -0.59
     handle
    -0.58
     bands
    -0.58
    enum
    -0.58
    ienne
    -0.57
     participates
    -0.56
     actionGroup
    -0.56
    aten
    -0.55
    shows
    -0.55
     saddle
    -0.55
    POSITIVE LOGITS
     overboard
    0.74
     ILCS
    0.73
     Kinnikuman
    0.73
    BuyableInstoreAndOnline
    0.69
    Room
    0.68
    agate
    0.67
    VERTISEMENT
    0.66
     Kafka
    0.64
     untold
    0.64
    CLASSIFIED
    0.62
    Activations Density 0.057%

    No Known Activations