Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 158
    Prev
    Next
    INDEX
    Explanations

    elements related to numerical and categorical data organization

    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
    =-=-=-=-=-=-=-=-
    -0.74
     ANG
    -0.66
     blot
    -0.64
     Highlands
    -0.64
    aster
    -0.62
     Realms
    -0.59
     Minute
    -0.59
     hue
    -0.58
     Handling
    -0.57
     bum
    -0.57
    POSITIVE LOGITS
    semble
    0.80
    gewater
    0.73
    hiba
    0.70
    training
    0.67
    cheon
    0.67
    rape
    0.64
    employ
    0.64
    heimer
    0.64
    heter
    0.64
    olf
    0.63
    Activations Density 1.482%

    No Known Activations