© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 592
    Prev
    Next
    INDEX
    Explanations

    references to corporate ownership and leadership

    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
    Episode
    -0.80
    wagen
    -0.69
    END
    -0.67
    �
    -0.65
    �
    -0.65
    ido
    -0.64
    ADE
    -0.64
    bard
    -0.63
    yle
    -0.62
    ACY
    -0.62
    POSITIVE LOGITS
     sleepy
    0.70
    undown
    0.66
    hops
    0.64
    rouse
    0.64
     noisy
    0.63
     visually
    0.63
    then
    0.61
     evenings
    0.60
     nause
    0.60
     startled
    0.60
    Activations Density 0.638%

    No Known Activations