© 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. 2601
    Prev
    Next
    INDEX
    Explanations

    references to specific years in a timeline

    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
    nesses
    -0.75
    ements
    -0.70
    ierrez
    -0.67
    EMBER
    -0.66
    ocations
    -0.62
    NESS
    -0.62
    usions
    -0.59
     respects
    -0.58
    ukong
    -0.56
    phia
    -0.56
    POSITIVE LOGITS
    ���
    0.80
     srf
    0.74
    christ
    0.68
    �
    0.64
     contag
    0.62
     pione
    0.59
    staking
    0.59
    ��
    0.57
    heed
    0.57
     derailed
    0.57
    Activations Density 0.087%

    No Known Activations