© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 2699
    Prev
    Next
    INDEX
    Explanations

    terms related to political systems, particularly in the context of the U.S. Constitution and its framers

    oai_token-act-pair · gpt-3.5-turbo

    references to the United States Constitution and its foundational principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jian
    -0.89
     Siem
    -0.86
    ibaba
    -0.85
     Hai
    -0.83
     Razer
    -0.81
    elight
    -0.79
    Tes
    -0.78
     Audi
    -0.78
    biz
    -0.77
    ellery
    -0.77
    POSITIVE LOGITS
     Constitution
    1.90
     Constitutional
    1.76
     constitutional
    1.63
     Founding
    1.58
     Founders
    1.49
     constitution
    1.48
     Amendment
    1.48
     Amendments
    1.45
     Clause
    1.43
    constitutional
    1.39
    Activations Density 0.526%

    No Known Activations