© 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. 0-RES-JB
    11. 12651
    Prev
    Next
    INDEX
    Explanations

    keywords related to sickness or medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to illness or being unwell

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Decoder
    -0.67
    forth
    -0.66
     Architecture
    -0.66
    _.
    -0.64
    ables
    -0.63
    atari
    -0.63
    arrell
    -0.63
    iture
    -0.62
    ano
    -0.62
     Dialogue
    -0.62
    POSITIVE LOGITS
     sick
    3.72
     Sick
    2.55
     sickness
    1.96
     nause
    1.38
     tired
    1.38
     illness
    1.35
     dise
    1.34
     ill
    1.32
     wounded
    1.28
     illnesses
    1.24
    Activations Density 0.019%

    No Known Activations