© 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. 10-RES-JB
    11. 15982
    Prev
    Next
    INDEX
    Explanations

    numbers related to sports statistics

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics and performance metrics, particularly in sports contexts

    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
    enegger
    -0.81
    uously
    -0.70
     Moj
    -0.70
     loudspe
    -0.66
     Turing
    -0.65
     nort
    -0.64
     Cater
    -0.64
     Bak
    -0.63
     Violet
    -0.63
     Instruments
    -0.62
    POSITIVE LOGITS
    %:
    1.14
    BIP
    1.08
    Avg
    1.02
    Score
    0.96
    Rate
    0.96
    %).
    0.93
    orsi
    0.92
    Percent
    0.91
    Hit
    0.91
    %,
    0.90
    Activations Density 0.124%

    No Known Activations