Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 8566
    Prev
    Next
    INDEX
    Explanations

    medical conditions, diseases, and vaccines

    oai_token-act-pair · gpt-3.5-turbo

    references to diseases and health-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.88
    eton
    -0.79
    umo
    -0.78
    pmwiki
    -0.78
    anke
    -0.77
    tarians
    -0.77
    fman
    -0.76
    yrinth
    -0.76
    quartered
    -0.74
    rade
    -0.74
    POSITIVE LOGITS
     hepatitis
    1.06
     Hep
    0.87
    hazard
    0.70
     vaccines
    0.70
     haze
    0.69
     vaccinations
    0.67
     contagious
    0.67
     Bran
    0.66
    cohol
    0.66
     737
    0.64
    Activations Density 0.017%

    No Known Activations