© 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. 520
    Prev
    Next
    INDEX
    Explanations

    instances of a specific symbol or punctuation character

    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
    orney
    -0.64
    interstitial
    -0.61
    ancial
    -0.61
    istical
    -0.59
    ista
    -0.58
     Rasmussen
    -0.55
     unspecified
    -0.54
     Lunar
    -0.54
     Aerospace
    -0.53
     Mandal
    -0.52
    POSITIVE LOGITS
    �
    0.83
    �
    0.75
    �
    0.75
    �
    0.74
    �
    0.73
    �
    0.71
    �
    0.71
    �
    0.70
    �
    0.69
    �
    0.69
    Activations Density 0.368%

    No Known Activations