© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 16400
    Prev
    Next
    INDEX
    Explanations

    information related to statistics in sports, especially focusing on measurements such as yards gained, carries, and touchdowns

    oai_token-act-pair · gpt-3.5-turbo

    statistics related to football yardage and scoring

    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
     Thrones
    -0.67
     Wik
    -0.66
     Regions
    -0.64
     Arn
    -0.63
     Lauder
    -0.62
     Wink
    -0.62
    enegger
    -0.62
     Mothers
    -0.62
     Murdoch
    -0.58
    Wiki
    -0.58
    POSITIVE LOGITS
     rushing
    1.28
     receiving
    1.12
     rusher
    1.07
     passing
    0.96
     scrimmage
    0.89
     touchdown
    0.88
     passer
    0.81
     receiver
    0.78
     Passing
    0.77
     offense
    0.76
    Activations Density 0.033%

    No Known Activations