© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 8282
    Prev
    Next
    INDEX
    Explanations

    terms related to health risks and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating increased health risks and medical conditions

    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
    DragonMagazine
    -1.13
    soDeliveryDate
    -0.80
    town
    -0.77
    izens
    -0.74
     Franch
    -0.73
    ĸļ
    -0.72
    wark
    -0.72
    minus
    -0.72
    amiliar
    -0.71
    xtap
    -0.71
    POSITIVE LOGITS
     cardiovascular
    1.46
     illness
    1.38
     diseases
    1.37
     disease
    1.34
     cancers
    1.33
     miscarriage
    1.31
     illnesses
    1.30
     infections
    1.26
     obesity
    1.25
     infection
    1.24
    Activations Density 0.197%

    No Known Activations