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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 660
    Prev
    Next
    INDEX
    Explanations

    references to specific measurements or statistics

    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
    arie
    -0.75
    edia
    -0.74
    kamp
    -0.71
    zos
    -0.70
    oran
    -0.70
    tesy
    -0.69
    iliated
    -0.69
    DOM
    -0.68
    edu
    -0.68
    tif
    -0.68
    POSITIVE LOGITS
     scent
    0.69
     Shroud
    0.66
     mosqu
    0.66
    head
    0.64
     Skydragon
    0.63
    heads
    0.62
    ön
    0.61
    HEAD
    0.60
    up
    0.60
     Swift
    0.60
    Activations Density 1.730%

    No Known Activations