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. 651
    Prev
    Next
    INDEX
    Explanations

    terms related to psychological concepts and conditions

    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
     hindsight
    -0.66
     retrospect
    -0.66
     compr
    -0.62
     refined
    -0.61
     parted
    -0.61
     evolution
    -0.60
     maturity
    -0.60
     Delete
    -0.59
     gen
    -0.59
     declass
    -0.59
    POSITIVE LOGITS
    lake
    0.82
    orthy
    0.77
    kas
    0.73
    other
    0.73
    osi
    0.72
    ould
    0.72
    olon
    0.70
     Tide
    0.69
    nos
    0.69
    ophysical
    0.69
    Activations Density 0.051%

    No Known Activations