© 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. 10-RES-JB
    11. 18486
    Prev
    Next
    INDEX
    Explanations

    keywords related to public health organizations, such as the Centers for Disease Control and Prevention (CDC)

    oai_token-act-pair · gpt-3.5-turbo

    terms related to disease and health organizations

    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
     hur
    -0.65
     trump
    -0.62
     axes
    -0.62
     shaved
    -0.61
    WHERE
    -0.59
     pas
    -0.59
     avail
    -0.58
     quart
    -0.58
     glim
    -0.57
    sticks
    -0.57
    POSITIVE LOGITS
     Control
    0.96
     Prevention
    0.83
     Outbreak
    0.75
     Epidem
    0.73
     Identification
    0.71
     Registry
    0.70
     Communication
    0.68
    iscovery
    0.67
     Reduction
    0.67
    Management
    0.67
    Activations Density 0.019%

    No Known Activations