© 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. 11-RES-JB
    11. 3597
    Prev
    Next
    INDEX
    Explanations

    phrases related to public health research and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to health organizations and public health initiatives

    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
    sbm
    -0.91
     Steele
    -0.80
    rade
    -0.77
     Aires
    -0.77
    lus
    -0.72
    notations
    -0.70
    Tesla
    -0.70
     audition
    -0.69
    é¾įåĸļ士
    -0.69
    lease
    -0.69
    POSITIVE LOGITS
     epidem
    1.52
     prevention
    1.49
     CDC
    1.47
    CDC
    1.46
     preventive
    1.41
     epidemic
    1.40
     pediatric
    1.36
     vaccination
    1.34
     obesity
    1.34
    AIDS
    1.34
    Activations Density 0.718%

    No Known Activations