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. 649
    Prev
    Next
    INDEX
    Explanations

    mentions of seasons in a sports context

    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
    Write
    -0.70
     deposition
    -0.62
     infancy
    -0.59
    #$
    -0.58
     adolesc
    -0.58
    uberty
    -0.56
     volts
    -0.56
     sclerosis
    -0.56
     Barron
    -0.55
     Lifetime
    -0.55
    POSITIVE LOGITS
     elsewhere
    0.79
     captcha
    0.72
    outside
    0.70
    ople
    0.69
    iscons
    0.67
     amongst
    0.64
    anooga
    0.64
    etsk
    0.63
    arter
    0.62
     somewhere
    0.62
    Activations Density 0.103%

    No Known Activations