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. 654
    Prev
    Next
    INDEX
    Explanations

    symbols or characters representing mockery or derogatory references

    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
     houses
    -0.73
     dirt
    -0.71
     intermedi
    -0.67
     hut
    -0.66
     house
    -0.66
     dwarf
    -0.63
     cle
    -0.62
     euph
    -0.62
     cre
    -0.61
     magnitude
    -0.60
    POSITIVE LOGITS
    ��
    1.03
    ーティ
    0.95
    entin
    0.88
    ACA
    0.86
    aeda
    0.85
    ��
    0.84
    atis
    0.84
    ��
    0.83
    amily
    0.83
    ivas
    0.82
    Activations Density 0.083%

    No Known Activations