© 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. 11-RES-JB
    11. 4869
    Prev
    Next
    INDEX
    Explanations

    terms related to health issues and medical conditions, including physical, psychological, neurological, and behavioral aspects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to health and medical conditions

    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
    ologue
    -0.73
    enhagen
    -0.71
     Alphabet
    -0.71
     Collective
    -0.70
    tyard
    -0.70
    Universal
    -0.69
    wark
    -0.69
    maxwell
    -0.68
     Catalog
    -0.66
    thouse
    -0.66
    POSITIVE LOGITS
     disorders
    1.47
     problems
    1.37
     disturbances
    1.36
     injuries
    1.34
     ailments
    1.33
     defects
    1.33
     illnesses
    1.32
     deficiencies
    1.29
     illness
    1.26
     complications
    1.26
    Activations Density 0.262%

    No Known Activations