© 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. 3233
    Prev
    Next
    INDEX
    Explanations

    references to data or statistics

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     flipped
    -0.72
     interacted
    -0.70
     morphed
    -0.69
    スト
    -0.68
     decon
    -0.67
     Dynamics
    -0.67
     orchestrated
    -0.66
     flips
    -0.65
     replicated
    -0.64
     programmed
    -0.64
    POSITIVE LOGITS
    ,—
    1.14
     Edition
    1.13
    æ
    0.97
    Pg
    0.95
    .—
    0.95
     afore
    0.94
    CHAPTER
    0.93
     brill
    0.91
    merce
    0.87
     thence
    0.86
    Activations Density 5.389%

    No Known Activations