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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 2-MLP
    11. 4495
    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
     \
    -0.07
    No
    -0.07
    Z
    -0.06
    J
    -0.05
     heap
    -0.05
    .time
    -0.05
    En
    -0.05
     Value
    -0.05
     colle
    -0.05
    Error
    -0.05
    POSITIVE LOGITS
     representing
    0.11
     '#
    0.09
     cur
    0.08
    reshold
    0.08
     ('
    0.07
     (-
    0.07
     The
    0.07
     Tuple
    0.07
     create
    0.07
     Returns
    0.06
    Activations Density 23.794%

    No Known Activations