© 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. 20355
    Prev
    Next
    INDEX
    Explanations

    keywords indicating different types of risks, especially related to health conditions

    oai_token-act-pair · gpt-3.5-turbo

    medical risk factors related to various diseases and 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
    notations
    -0.77
     largeDownload
    -0.76
    ©¶æ¥µ
    -0.76
    soDeliveryDate
    -0.75
    minus
    -0.72
    =-=-=-=-
    -0.72
    ãĤĵ
    -0.72
    ĸļ
    -0.70
    DragonMagazine
    -0.69
    town
    -0.69
    POSITIVE LOGITS
     cardiovascular
    1.18
     developing
    1.14
     coronary
    1.05
     mortality
    1.04
     illness
    1.04
     accidents
    1.04
     diseases
    1.03
     disease
    1.01
     suicide
    1.00
     cancers
    0.99
    Activations Density 0.144%

    No Known Activations