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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RES-JB
    11. 12843
    Prev
    Next
    INDEX
    Explanations

    keywords related to sports statistics, such as player performances and game outcomes

    oai_token-act-pair · gpt-3.5-turbo

    references to competition or matches involving teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wcs
    -0.94
    udder
    -0.91
    lus
    -0.89
    ouf
    -0.87
    olitan
    -0.83
    zl
    -0.83
    overed
    -0.82
    collar
    -0.82
    lux
    -0.79
    jar
    -0.79
    POSITIVE LOGITS
     opponents
    0.92
     against
    0.86
     opponent
    0.82
     foes
    0.81
     Against
    0.74
     adversaries
    0.70
     Kansas
    0.69
     batters
    0.68
     anybody
    0.68
     Vader
    0.67
    Activations Density 0.042%

    No Known Activations