© 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. 4-RES-JB
    11. 10462
    Prev
    Next
    INDEX
    Explanations

    terms related to health insurance regulation within the context of public policy discussions

    oai_token-act-pair · gpt-3.5-turbo

    references to health insurance and its related aspects

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

    No Comments

    Negative Logits
    angular
    -0.77
     Hoo
    -0.75
    urb
    -0.75
    ather
    -0.73
     Earthqu
    -0.73
     Riy
    -0.72
     IMAGES
    -0.72
     BST
    -0.70
    stanbul
    -0.70
    zel
    -0.69
    POSITIVE LOGITS
    amacare
    1.28
     providers
    1.09
     premiums
    1.04
     vouchers
    1.00
     beneficiaries
    0.96
     ObamaCare
    0.95
     insurance
    0.94
     reimburse
    0.94
     eligibility
    0.92
     subsidies
    0.91
    Activations Density 0.069%

    No Known Activations