© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 8116
    Prev
    Next
    INDEX
    Explanations

    baseball-related terms, specifically focusing on game situations and pitcher performance

    oai_token-act-pair · gpt-3.5-turbo

    references to baseball innings and related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dra
    -0.71
     Trave
    -0.68
    Nev
    -0.63
     Char
    -0.62
    â
    -0.62
    aine
    -0.62
    ë
    -0.60
    bus
    -0.60
     VIS
    -0.58
     Travel
    -0.58
    POSITIVE LOGITS
     inning
    3.48
     innings
    2.15
     bullpen
    1.79
     reliever
    1.60
     infield
    1.57
     pitcher
    1.52
     outfielder
    1.51
    inning
    1.50
     outfield
    1.47
     baseman
    1.44
    Activations Density 0.013%

    No Known Activations