© 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. 1341
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols used for emphasis or separation

    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
    alian
    -0.73
     proportion
    -0.69
     Paramount
    -0.67
     denomin
    -0.63
    NI
    -0.59
     Kyr
    -0.59
     underestimate
    -0.59
     Nielsen
    -0.58
     Frie
    -0.58
    luaj
    -0.58
    POSITIVE LOGITS
    �
    0.73
    course
    0.69
    �
    0.69
    �
    0.67
    �
    0.66
    insert
    0.66
    onte
    0.65
    uties
    0.65
     theirs
    0.64
    inctions
    0.64
    Activations Density 0.076%

    No Known Activations