© 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. 8-RES-JB
    11. 2239
    Prev
    Next
    INDEX
    Explanations

    keywords related to health insurance coverage and policies

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to health insurance and coverage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oric
    -0.76
    cia
    -0.73
     Hoo
    -0.70
    lins
    -0.70
    oder
    -0.70
    ograp
    -0.70
    flies
    -0.68
    otor
    -0.67
    shire
    -0.67
    orically
    -0.67
    POSITIVE LOGITS
    amacare
    1.12
     rebate
    1.06
     premiums
    1.02
     eligibility
    1.00
     uninsured
    1.00
     providers
    0.96
     reimburse
    0.94
     enrol
    0.94
     reimbursement
    0.92
     Medicaid
    0.91
    Activations Density 0.112%

    No Known Activations