© 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. 0-RES-JB
    11. 5125
    Prev
    Next
    INDEX
    Explanations

    mentions of toilet-related objects or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to toilets and related sanitation issues

    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
    Adds
    -0.72
    son
    -0.71
    MS
    -0.69
    hips
    -0.68
     Targ
    -0.68
    Brandon
    -0.68
     Sloan
    -0.66
     Briggs
    -0.65
    Rad
    -0.63
     Brandon
    -0.63
    POSITIVE LOGITS
     toilet
    3.72
     toilets
    2.83
     restroom
    2.12
     bathroom
    2.10
    ilet
    2.06
     toile
    1.81
     restrooms
    1.71
     bathrooms
    1.70
     pee
    1.45
     poop
    1.42
    Activations Density 0.014%

    No Known Activations