Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 11044
    Prev
    Next
    INDEX
    Explanations

    phrases related to a fictional or real-life person named Bruce

    oai_token-act-pair · gpt-3.5-turbo

    the name "Bruce" in various contexts

    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
    words
    -0.75
    xual
    -0.70
    encing
    -0.68
    edited
    -0.66
    sweet
    -0.63
    ships
    -0.63
    mons
    -0.62
    align
    -0.62
    dayName
    -0.61
    ours
    -0.61
    POSITIVE LOGITS
     Jenner
    1.17
     Schne
    1.11
     Willis
    1.03
     Banner
    0.90
     Spring
    0.87
     Wayne
    0.87
     Campbell
    0.81
     Almighty
    0.81
     Fein
    0.80
     Lee
    0.80
    Activations Density 0.045%

    No Known Activations