© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 2958
    Prev
    Next
    INDEX
    Explanations

    closing parentheses or punctuation marks indicating the end of a statement

    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
    Untitled
    -0.56
    pedia
    -0.56
     shack
    -0.54
    stones
    -0.53
    Wiki
    -0.53
    pload
    -0.52
     Abraham
    -0.51
     Babylon
    -0.50
    von
    -0.50
    田
    -0.50
    POSITIVE LOGITS
    ecause
    0.68
    lication
    0.64
    sembly
    0.60
     etc
    0.57
     .)
    0.57
    ategories
    0.57
    igers
    0.57
    udeb
    0.56
    onne
    0.56
    .):
    0.55
    Activations Density 0.159%

    No Known Activations