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. 3-RES-JB
    6. 19504
    Prev
    Next
    INDEX
    Explanations

    references to a person named "Bron" with varying levels of activation, potentially indicating it's focusing on different individuals with the same or similar names

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Bron."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EPA
    -0.73
    aeda
    -0.72
    uras
    -0.69
    URA
    -0.68
    yrinth
    -0.66
     Biological
    -0.65
    Known
    -0.63
    Fed
    -0.63
    ARR
    -0.63
    RESULTS
    -0.61
    POSITIVE LOGITS
    fman
    1.20
    wyn
    1.03
    zes
    1.01
    etooth
    0.91
     Bron
    0.90
    hm
    0.90
    zos
    0.90
    ze
    0.87
    zon
    0.87
    hma
    0.85
    Activations Density 0.008%

    No Known Activations