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. 657
    Prev
    Next
    INDEX
    Explanations

    references to consecutive achievements or events over multiple periods

    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
    asus
    -0.92
    izabeth
    -0.87
    ipal
    -0.74
    bons
    -0.72
    prises
    -0.71
    impact
    -0.70
    ser
    -0.69
    iple
    -0.66
    sole
    -0.66
    devices
    -0.65
    POSITIVE LOGITS
     time
    0.83
    edin
    0.77
     Masquerade
    0.73
    Tx
    0.72
     consecutive
    0.71
     year
    0.64
    BC
    0.62
     times
    0.61
     Time
    0.59
     straight
    0.59
    Activations Density 0.017%

    No Known Activations