© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18797
    Prev
    Next
    INDEX
    Explanations

    phrases related to health insurance and government healthcare policies

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to healthcare policies and regulations

    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
     arte
    -0.97
     Chess
    -0.90
    Dialogue
    -0.87
     Kubrick
    -0.86
    artifacts
    -0.86
     curator
    -0.85
     extrad
    -0.81
     graffiti
    -0.80
     poaching
    -0.79
    elaide
    -0.78
    POSITIVE LOGITS
     Medicaid
    1.90
     uninsured
    1.87
     Obamacare
    1.86
    amacare
    1.78
     ACA
    1.77
     ObamaCare
    1.75
     HHS
    1.69
     insurers
    1.68
     Medicare
    1.65
     Affordable
    1.62
    Activations Density 0.648%

    No Known Activations