© 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. 1458
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of "the" in various contexts

    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
    heit
    -0.72
    omics
    -0.67
    arians
    -0.64
    holm
    -0.64
    Availability
    -0.64
     Returns
    -0.63
    Others
    -0.63
    AppData
    -0.62
    VP
    -0.62
    ftime
    -0.61
    POSITIVE LOGITS
    ollower
    0.78
     Trace
    0.76
     Guardian
    0.71
     Intercept
    0.69
     Associated
    0.67
     Globe
    0.64
    interstitial
    0.64
    uyomi
    0.63
    ��
    0.62
    utch
    0.61
    Activations Density 0.074%

    No Known Activations