© 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. 1-RES-JB
    11. 16771
    Prev
    Next
    INDEX
    Explanations

    mentions of people or characters wearing specific items of clothing

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "wearing"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edia
    -0.75
     Purg
    -0.67
     Sources
    -0.64
    prep
    -0.64
    Fund
    -0.64
     Democr
    -0.63
    Publisher
    -0.63
    analysis
    -0.62
    Torrent
    -0.62
    ����
    -0.61
    POSITIVE LOGITS
     worn
    1.23
     wearer
    1.13
     wear
    1.13
     apparel
    1.10
     wore
    1.09
     clothing
    1.01
     wearing
    1.00
     jeans
    0.97
     uniforms
    0.97
     wears
    0.97
    Activations Density 0.012%

    No Known Activations