© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 2-MLP
    11. 4928
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    un
    -0.09
     each
    -0.08
    _dep
    -0.04
    umn
    -0.04
    }"
    -0.04
    ("
    -0.04
     depth
    -0.03
     dep
    -0.03
     O
    -0.03
    ')↵↵
    -0.03
    POSITIVE LOGITS
    ho
    0.12
    ]['
    0.09
     {'
    0.08
     {"
    0.08
    ({
    0.07
    ave
    0.05
    01
    0.05
     {↵
    0.05
     t
    0.04
    "{
    0.04
    Activations Density 7.216%

    No Known Activations