© 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. 3209
    Prev
    Next
    INDEX
    Explanations

    repeated references to the term "Platinum."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    ��
    -0.69
    roph
    -0.66
    ��
    -0.63
    SEA
    -0.63
    PASS
    -0.63
    ��
    -0.61
     epit
    -0.60
    ------------------------------------------------
    -0.59
    KING
    -0.59
    RECT
    -0.57
    POSITIVE LOGITS
    umbing
    1.09
    ausible
    0.99
    umed
    0.92
    umb
    0.88
    ural
    0.88
    amen
    0.87
    acements
    0.86
    acement
    0.85
    ause
    0.83
    ummy
    0.82
    Activations Density 0.031%

    No Known Activations