© 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. 1256
    Prev
    Next
    INDEX
    Explanations

    references to rankings or categorizations of excellence

    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
     handshake
    -0.73
     scrimmage
    -0.69
     truths
    -0.67
     plunge
    -0.65
     farewell
    -0.65
     eviction
    -0.65
    ongevity
    -0.62
     toast
    -0.62
     clinch
    -0.62
     NFC
    -0.61
    POSITIVE LOGITS
    atto
    0.78
    stud
    0.78
    eff
    0.71
    expensive
    0.69
    tek
    0.68
    demand
    0.68
    matched
    0.67
    fin
    0.66
    Aud
    0.66
    lay
    0.65
    Activations Density 0.015%

    No Known Activations