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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 460
    Prev
    Next
    INDEX
    Explanations

    the repetition of the word "the."

    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
    terms
    -0.74
    ey
    -0.70
    rodu
    -0.68
    tics
    -0.67
    ----------
    -0.67
    grades
    -0.67
     Missions
    -0.66
    ser
    -0.65
    iod
    -0.64
    STEM
    -0.63
    POSITIVE LOGITS
    ��
    0.81
    urer
    0.79
    orie
    0.73
    luaj
    0.69
     mole
    0.67
     amygdala
    0.64
     Orion
    0.63
    ossibility
    0.62
     dreaded
    0.62
    oire
    0.61
    Activations Density 0.133%

    No Known Activations