© 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. 9448
    Prev
    Next
    INDEX
    Explanations

    phrases related to bodily systems and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the human circulatory and urinary systems

    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
    Trend
    -0.74
    Weather
    -0.73
    lvl
    -0.72
     Trend
    -0.72
    equality
    -0.72
     Attribution
    -0.71
     Samurai
    -0.71
    Gaming
    -0.71
     Doomsday
    -0.71
    Merit
    -0.70
    POSITIVE LOGITS
     muc
    1.62
     intestine
    1.56
     bowel
    1.52
     intestinal
    1.49
     lymph
    1.47
     digestive
    1.47
     intest
    1.45
     bloodstream
    1.44
     saliva
    1.41
     gastro
    1.40
    Activations Density 0.223%

    No Known Activations