© 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. 2752
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the" and references to specific time periods

    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
    ledge
    -0.75
    eks
    -0.70
    cipled
    -0.69
    Market
    -0.68
     aimed
    -0.65
    chance
    -0.65
    ocations
    -0.65
    ulla
    -0.64
    ribution
    -0.64
    icas
    -0.63
    POSITIVE LOGITS
     Intermediate
    0.69
     Doctrine
    0.66
     RSA
    0.66
     course
    0.63
    NRS
    0.62
     Newsp
    0.61
     Miracle
    0.61
     Revolutionary
    0.59
    Alert
    0.59
     1800
    0.58
    Activations Density 0.068%

    No Known Activations