© 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. 866
    Prev
    Next
    INDEX
    Explanations

    references to a specific team or organization that starts with 'Q'

    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
    Initialized
    -0.61
     affili
    -0.59
     trenches
    -0.59
     ACTIONS
    -0.58
    arily
    -0.57
    lessly
    -0.56
     bailed
    -0.56
     RET
    -0.56
     Ivy
    -0.56
    itatively
    -0.56
    POSITIVE LOGITS
    sson
    0.70
    UE
    0.70
     cumbers
    0.69
    BW
    0.69
    aram
    0.67
    lex
    0.67
    Quantity
    0.67
    ld
    0.67
    ures
    0.67
    wer
    0.66
    Activations Density 0.017%

    No Known Activations