© 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. 17400
    Prev
    Next
    INDEX
    Explanations

    health-related phrases and terms, particularly related to medical procedures and transplantation

    oai_token-act-pair · gpt-3.5-turbo

    information related to medical conditions and organ transplants

    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
    trak
    -0.85
    fleet
    -0.82
     Subtle
    -0.82
     à¨
    -0.77
     occup
    -0.77
    wx
    -0.76
    awks
    -0.75
    ithmetic
    -0.74
    andals
    -0.72
    awk
    -0.72
    POSITIVE LOGITS
     embryos
    1.81
     transplant
    1.78
     embryo
    1.64
     transpl
    1.63
     cloning
    1.60
     sperm
    1.59
     donor
    1.54
     infertility
    1.50
     Canaver
    1.43
     kidneys
    1.41
    Activations Density 0.190%

    No Known Activations