© 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. 11-RES-JB
    11. 17340
    Prev
    Next
    INDEX
    Explanations

    metrics and statistics related to sports performance

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe statistics and performance metrics in sports

    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
    wrong
    -0.72
    soon
    -0.71
    cms
    -0.70
    onian
    -0.69
    uary
    -0.69
    Acknowled
    -0.68
    yg
    -0.67
    Synopsis
    -0.67
    ipedia
    -0.67
    FY
    -0.65
    POSITIVE LOGITS
    stood
    0.97
     RIS
    0.97
     averages
    0.91
     Norfolk
    0.91
     runners
    0.88
     seven
    0.85
     eight
    0.84
     Tampa
    0.81
     nine
    0.81
     six
    0.80
    Activations Density 0.080%

    No Known Activations