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. 19861
    Prev
    Next
    INDEX
    Explanations

    words related to sports, particularly basketball

    oai_token-act-pair · gpt-3.5-turbo

    references to basketball and related sports

    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
    ablishment
    -0.78
    ktop
    -0.67
    ainer
    -0.64
     Rate
    -0.62
    ignt
    -0.62
    imate
    -0.61
    mble
    -0.61
    Border
    -0.61
    wered
    -0.60
    omething
    -0.60
    POSITIVE LOGITS
     stadiums
    0.95
     scholarships
    0.86
     leagues
    0.82
     clubs
    0.82
     players
    0.81
     tournaments
    0.81
     referees
    0.80
     balls
    0.80
     scholarship
    0.79
     league
    0.79
    Activations Density 0.046%

    No Known Activations