© 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. 3316
    Prev
    Next
    INDEX
    Explanations

    references to related content or topics

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     pains
    -0.71
     joking
    -0.69
     purposes
    -0.68
    ividual
    -0.64
     interested
    -0.64
     characters
    -0.63
     bothered
    -0.63
     motivated
    -0.63
     specimens
    -0.61
     entrants
    -0.60
    POSITIVE LOGITS
     ►
    0.83
    ingle
    0.71
     ├
    0.70
    fall
    0.67
    conom
    0.67
    oufl
    0.67
    ˜
    0.66
     REST
    0.65
    ilot
    0.65
    merce
    0.65
    Activations Density 0.011%

    No Known Activations