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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11-RES-JB
    6. 2769
    Prev
    Next
    INDEX
    Explanations

    information related to numbers of people and quantities affected by health insurance coverage and access to healthcare

    oai_token-act-pair · gpt-3.5-turbo

    references to large numbers of people affected by social and health 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
    inventoryQuantity
    -0.78
    wcsstore
    -0.75
    VPN
    -0.72
     Dating
    -0.71
    ulkan
    -0.69
    enture
    -0.69
     embr
    -0.69
    DragonMagazine
    -0.68
    ãĤ´ãĥ³
    -0.68
    ibal
    -0.67
    POSITIVE LOGITS
     Americans
    1.46
     Californ
    1.14
     uninsured
    1.13
    Americans
    1.12
     households
    1.10
     Texans
    1.09
     families
    1.04
     Canadians
    0.99
     American
    0.99
     Australians
    0.98
    Activations Density 0.159%

    No Known Activations