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. 22796
    Prev
    Next
    INDEX
    Explanations

    sports-related terms and game statistics, particularly numbers related to scores, points, and player performances

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics related to scoring and performance in 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
    DragonMagazine
    -0.90
    actionDate
    -0.72
    LER
    -0.70
    leneck
    -0.68
    hra
    -0.66
    phant
    -0.65
    study
    -0.65
    fecture
    -0.65
    agonist
    -0.65
    ragon
    -0.65
    POSITIVE LOGITS
     unanswered
    1.04
     consecutive
    1.00
     straight
    0.99
    teenth
    0.95
     successive
    0.92
    straight
    0.91
     assists
    0.90
     pointers
    0.89
     turnovers
    0.89
     apiece
    0.87
    Activations Density 0.094%

    No Known Activations