© 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 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. 14951
    Prev
    Next
    INDEX
    Explanations

    specific medical conditions, statistics, and numbers

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics related to health outcomes 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
    wcsstore
    -0.80
    ļéĨĴ
    -0.79
     srfAttach
    -0.78
     Vendor
    -0.74
    âķIJ
    -0.71
    âķIJâķIJ
    -0.68
     Barg
    -0.66
    sbm
    -0.64
    Commerce
    -0.64
     Compass
    -0.64
    POSITIVE LOGITS
     deaths
    1.59
     mortality
    1.43
     Deaths
    1.37
     morbid
    1.31
     fatalities
    1.25
     hospitalized
    1.20
    death
    1.20
     fatal
    1.17
     death
    1.16
     cancers
    1.12
    Activations Density 0.280%

    No Known Activations