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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 2138
    Prev
    Next
    INDEX
    Explanations

    parentheses and their associated content in the text

    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
    ーテ
    -0.52
    VALUE
    -0.47
    icular
    -0.47
    CLASSIFIED
    -0.46
    eele
    -0.45
    vals
    -0.43
     resembled
    -0.43
    ?????-
    -0.42
    cade
    -0.42
    Introduced
    -0.42
    POSITIVE LOGITS
     Hok
    0.46
     WH
    0.37
     Princ
    0.37
     CAN
    0.37
     Gh
    0.36
     Pr
    0.36
     Sent
    0.35
     Har
    0.35
     PR
    0.35
     Am
    0.35
    Activations Density 1.141%

    No Known Activations