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. 7291
    Prev
    Next
    INDEX
    Explanations

    statistics related to sports, specifically baseball and possibly other sports as well

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics related to sports performance

    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
     Lauder
    -0.71
    arant
    -0.65
    larg
    -0.61
    udeb
    -0.61
    photos
    -0.59
    nect
    -0.58
     Matters
    -0.58
    onday
    -0.58
     caption
    -0.57
    umably
    -0.57
    POSITIVE LOGITS
     GPA
    0.86
     assists
    0.83
     ERA
    0.79
     assist
    0.71
    GHz
    0.69
     sacks
    0.69
     goals
    0.66
     adjusted
    0.66
     avg
    0.64
     cumulative
    0.63
    Activations Density 0.026%

    No Known Activations