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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 974
    Prev
    Next
    INDEX
    Explanations

    significant historical years or timestamps

    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
     distingu
    -0.65
    ��
    -0.65
    leases
    -0.64
    Serial
    -0.62
    etheless
    -0.60
    rators
    -0.60
     repr
    -0.60
    anmar
    -0.60
    uador
    -0.59
     acknow
    -0.59
    POSITIVE LOGITS
    daq
    0.65
     READ
    0.61
    akia
    0.61
     Alley
    0.59
    elin
    0.59
     anymore
    0.59
    FOR
    0.59
    DOS
    0.58
    ella
    0.58
     risk
    0.57
    Activations Density 0.085%

    No Known Activations