© 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
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 1378
    Prev
    Next
    INDEX
    Explanations

    references to the Congressional Budget Office and related congressional activities

    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
    dayName
    -0.89
    --------------------------------------------------------
    -0.71
    ENCY
    -0.69
     depended
    -0.69
     ├
    -0.67
                    
    -0.67
    ć
    -0.66
    externalActionCode
    -0.64
     secondly
    -0.64
    ":[{"
    -0.64
    POSITIVE LOGITS
    aft
    0.65
    veyard
    0.63
    ��
    0.62
    adow
    0.61
    odox
    0.61
    aucas
    0.60
    isexual
    0.60
    athed
    0.60
    grave
    0.60
    committee
    0.60
    Activations Density 0.022%

    No Known Activations