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. 10-RES-JB
    6. 18187
    Prev
    Next
    INDEX
    Explanations

    names of sports players

    oai_token-act-pair · gpt-3.5-turbo

    names of athletes and sports figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rowling
    -0.96
     Fiona
    -0.81
     Tolkien
    -0.75
     Editorial
    -0.75
     Tablet
    -0.74
     editorial
    -0.72
     Geral
    -0.70
     Sonia
    -0.70
     Feminist
    -0.68
     Roh
    -0.68
    POSITIVE LOGITS
    essel
    0.78
    kowski
    0.75
     injury
    0.75
    ongo
    0.73
    acion
    0.73
    zyk
    0.72
    asley
    0.71
    zinski
    0.71
    oyer
    0.71
     injuries
    0.70
    Activations Density 0.167%

    No Known Activations