© 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. 516
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the letter 'A' at the beginning of words or phrases

    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
    Allow
    -0.69
     automatic
    -0.62
     honoured
    -0.61
     defe
    -0.60
     extends
    -0.60
     enchantment
    -0.60
     pets
    -0.60
     forgiven
    -0.59
     invalid
    -0.59
     outfield
    -0.59
    POSITIVE LOGITS
    sha
    0.79
    thia
    0.74
    mber
    0.73
    urdue
    0.72
    cmp
    0.72
    teenth
    0.71
    kai
    0.68
    uckland
    0.68
    heastern
    0.68
     spokesman
    0.68
    Activations Density 0.076%

    No Known Activations