© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 3334
    Prev
    Next
    INDEX
    Explanations

    the repeated use of the word "the" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    hm
    -0.63
    abel
    -0.61
    roach
    -0.60
    yet
    -0.58
     grou
    -0.57
    heit
    -0.56
     squarely
    -0.56
     demonstrating
    -0.56
    AMI
    -0.56
    hillary
    -0.55
    POSITIVE LOGITS
     meantime
    0.86
     end
    0.84
     absence
    0.74
     rush
    0.70
     minds
    0.69
    deen
    0.68
     case
    0.67
     midst
    0.67
    gar
    0.66
     intervening
    0.64
    Activations Density 0.068%

    No Known Activations