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. 17630
    Prev
    Next
    INDEX
    Explanations

    sports statistics, particularly shooting percentages and field goal percentages

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics and performance metrics related to 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
    zai
    -0.73
    onym
    -0.67
    ORGE
    -0.61
    holder
    -0.60
     insign
    -0.58
     Sax
    -0.58
     anx
    -0.57
    neau
    -0.55
    ophon
    -0.55
     laure
    -0.55
    POSITIVE LOGITS
     conversions
    0.80
     attempts
    0.80
     passes
    0.78
     shots
    0.78
     FG
    0.77
     shooting
    0.76
    pointers
    0.74
    downs
    0.72
     throws
    0.71
     foul
    0.71
    Activations Density 0.150%

    No Known Activations