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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16428
    Prev
    Next
    INDEX
    Explanations

    names related to health organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to health organizations and their reports related to disease control and prevention

    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
    rawdownloadcloneembedreportprint
    -0.72
    yip
    -0.71
     Strongh
    -0.67
    dale
    -0.67
    ¬¼
    -0.67
    issance
    -0.66
    Lord
    -0.64
    ML
    -0.64
    stand
    -0.63
    yss
    -0.63
    POSITIVE LOGITS
     Prevention
    0.99
    illance
    0.78
     Diseases
    0.76
     infectious
    0.76
     Medicine
    0.75
     Outbreak
    0.73
     Epidem
    0.72
     Tropical
    0.71
     Monitor
    0.71
     Policy
    0.71
    Activations Density 0.044%

    No Known Activations