© 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. 4877
    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
     break
    -0.08
    (list
    -0.06
    list
    -0.05
    List
    -0.05
     list
    -0.05
     List
    -0.04
    _list
    -0.04
    -0.04
    -0.04
    -0.03
    POSITIVE LOGITS
     given
    0.06
    instance
    0.06
    endoftext
    0.05
    ree
    0.03
    ri
    0.02
     visited
    0.02
    location
    0.02
     r
    0.01
     def
    0.01
    v
    0.01
    Activations Density 26.977%

    No Known Activations