© 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. 2937
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate relationships or connections between items or concepts

    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
    ety
    -0.65
    ENTS
    -0.65
    aeda
    -0.65
    ablishment
    -0.62
    apolis
    -0.60
    oros
    -0.57
    acco
    -0.56
    alde
    -0.55
    antly
    -0.54
    OV
    -0.54
    POSITIVE LOGITS
     which
    2.03
    which
    1.69
     whom
    1.49
     Which
    1.47
    Which
    1.36
     whose
    1.36
    whose
    1.19
     wherein
    1.09
     whence
    1.07
     whereby
    0.94
    Activations Density 1.289%

    No Known Activations