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. 9-TRES-DC
    6. 648
    Prev
    Next
    INDEX
    Explanations

    terms related to self-regulation

    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
     dwind
    -0.73
     cowardly
    -0.73
     coward
    -0.67
     pacif
    -0.67
     abstinence
    -0.67
     disbanded
    -0.66
     nonviolent
    -0.66
     nobility
    -0.66
     brave
    -0.65
     humane
    -0.64
    POSITIVE LOGITS
    address
    0.82
    description
    0.82
    ident
    0.78
    rating
    0.77
    reports
    0.74
    rated
    0.73
    Rating
    0.73
    selection
    0.72
    eval
    0.72
    icer
    0.71
    Activations Density 0.018%

    No Known Activations