© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20060
    Prev
    Next
    INDEX
    Explanations

    words related to bodily functions involving urination

    oai_token-act-pair · gpt-3.5-turbo

    references to bodily functions, specifically urination

    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
     MSI
    -0.73
     hel
    -0.68
     restoration
    -0.67
     Mod
    -0.66
     distribution
    -0.65
     return
    -0.64
     MOD
    -0.64
     rad
    -0.62
     architecture
    -0.62
     orche
    -0.62
    POSITIVE LOGITS
    pee
    5.07
    pees
    4.55
     pee
    1.75
    abee
    1.17
    kee
    1.17
    gee
    1.05
    oola
    1.05
    puff
    1.02
    awei
    0.98
    bles
    0.95
    Activations Density 0.015%

    No Known Activations