© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 20398
    Prev
    Next
    INDEX
    Explanations

    words related to legal or political matters, specifically focusing on constitutional concerns

    oai_token-act-pair · gpt-3.5-turbo

    references to constitutional matters and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yang
    -0.73
     Shed
    -0.71
    ilon
    -0.70
    Score
    -0.68
     anecd
    -0.68
    ynthesis
    -0.67
    chain
    -0.67
    nas
    -0.66
     Afric
    -0.66
    pora
    -0.66
    POSITIVE LOGITS
     amendment
    1.14
     amendments
    1.10
     Amendments
    1.01
     monarchy
    1.00
     Amendment
    0.98
     rights
    0.95
     republic
    0.92
     validity
    0.92
     violations
    0.91
     protections
    0.91
    Activations Density 0.032%

    No Known Activations