Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Dunefsky · Chlenski · Transcoders Enable Fine-Grained Interpretable Circuit Analysis
    3. GPT2-Small
    4. Transcoders Residuals
    5. 8-TRES-DC
    6. 7
    Prev
    Next
    INDEX
    Explanations

    periods of reflection or closure in a narrative

    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
    ties
    -0.63
    give
    -0.61
    PASS
    -0.61
     guessed
    -0.60
     measurement
    -0.60
     careg
    -0.59
    seekers
    -0.58
    ignment
    -0.58
     genders
    -0.58
     hypothesized
    -0.57
    POSITIVE LOGITS
     Like
    0.85
     Proceed
    0.83
     Consider
    0.83
     Every
    0.82
     Heck
    0.77
     Possibly
    0.75
     Because
    0.75
    Whereas
    0.75
     Again
    0.73
     Of
    0.73
    Activations Density 0.618%

    No Known Activations