Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 4595
    Prev
    Next
    INDEX
    Explanations

    phrases related to healthcare coverage, insurance, and the uninsured

    oai_token-act-pair · gpt-3.5-turbo

    terms related to insurance status, particularly focusing on the uninsured

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OTE
    -0.84
     Rapp
    -0.81
    nan
    -0.77
    ovie
    -0.76
    azine
    -0.74
    OPA
    -0.73
    wcsstore
    -0.71
    AMS
    -0.70
    ames
    -0.68
    EFF
    -0.68
    POSITIVE LOGITS
     uninsured
    1.17
    insured
    0.77
     mortality
    0.75
    ordable
    0.75
     premiums
    0.73
     carriers
    0.70
    uates
    0.69
     coverage
    0.69
     insured
    0.68
     insurance
    0.66
    Activations Density 0.006%

    No Known Activations