© 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
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 1093
    Prev
    Next
    INDEX
    Explanations

    references to emerging phenomena or significant developments

    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
    pn
    -0.65
    ulia
    -0.63
    faced
    -0.62
    uff
    -0.61
    anders
    -0.60
    nikov
    -0.59
    eric
    -0.59
    fing
    -0.59
    answered
    -0.59
    orative
    -0.59
    POSITIVE LOGITS
     known
    1.04
     regarded
    0.79
     Known
    0.73
     an
    0.72
     a
    0.72
    known
    0.69
     termed
    0.65
     dubbed
    0.64
     considered
    0.64
     characterized
    0.62
    Activations Density 1.019%

    No Known Activations