© 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. 1373
    Prev
    Next
    INDEX
    Explanations

    instances of periods, indicating the end of sentences in the text

    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
    lihood
    -0.58
    istrate
    -0.58
     creep
    -0.57
    nesota
    -0.55
    fts
    -0.54
     Juda
    -0.53
     Spart
    -0.52
    atility
    -0.52
    esty
    -0.51
     lakh
    -0.51
    POSITIVE LOGITS
        
    0.67
    :]
    0.63
    ********
    0.60
     VIDEOS
    0.60
    hester
    0.59
     boards
    0.57
    =-=-=-=-
    0.56
     [+
    0.56
     Cue
    0.56
    -------------
    0.56
    Activations Density 0.646%

    No Known Activations