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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 2668
    Prev
    Next
    INDEX
    Explanations

    topics related to discrimination and social justice

    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
    together
    -0.74
    endi
    -0.73
    cin
    -0.63
     Monte
    -0.60
     SUM
    -0.59
     Palest
    -0.58
     Repe
    -0.58
    .","
    -0.58
     withd
    -0.58
    soever
    -0.57
    POSITIVE LOGITS
    Race
    0.80
     race
    0.75
     stature
    0.74
    atures
    0.70
     chromosomes
    0.67
     ethnicity
    0.67
    race
    0.66
    ector
    0.65
     nationality
    0.65
     gender
    0.65
    Activations Density 0.092%

    No Known Activations