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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 24411
    Prev
    Next
    INDEX
    Explanations

    words related to various medical conditions and health risks, including diabetes, cancer, heart disease, obesity, and depression

    oai_token-act-pair · gpt-3.5-turbo

    references to health-related risks and diseases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    selage
    -0.88
    ciples
    -0.87
    âķIJ
    -0.84
     Companies
    -0.83
    uese
    -0.82
    agents
    -0.80
    ateurs
    -0.80
    soDeliveryDate
    -0.79
    acters
    -0.78
    amera
    -0.78
    POSITIVE LOGITS
     disease
    1.42
     asthma
    1.41
     depression
    1.40
     inflammation
    1.39
     illness
    1.39
     diseases
    1.37
     respiratory
    1.37
     arthritis
    1.36
     malnutrition
    1.35
     illnesses
    1.35
    Activations Density 0.221%

    No Known Activations