© 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. 3287
    Prev
    Next
    INDEX
    Explanations

    references to large population statistics or estimates

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    chnology
    -0.80
    illard
    -0.80
    phant
    -0.75
    unker
    -0.73
    ombo
    -0.73
    ████████
    -0.73
    KE
    -0.73
    ��
    -0.73
    ropolis
    -0.71
     Coffin
    -0.71
    POSITIVE LOGITS
     casual
    0.78
     registered
    0.76
     beginners
    0.75
     repeat
    0.75
     eligible
    0.74
     beginner
    0.71
     acres
    0.70
     diapers
    0.68
     homes
    0.67
     trips
    0.67
    Activations Density 0.029%

    No Known Activations