© 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. 4-RES-JB
    11. 13542
    Prev
    Next
    INDEX
    Explanations

    words related to soccer matches

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "match" and its variations in various contexts

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

    No Comments

    Negative Logits
    é»Ĵ
    -0.76
    ä¼
    -0.72
    sonian
    -0.70
    ä½ľ
    -0.70
    eous
    -0.69
    raft
    -0.69
    achev
    -0.68
    keye
    -0.67
    ãģķ
    -0.63
    Ire
    -0.62
    POSITIVE LOGITS
    making
    0.86
    maker
    0.85
    makers
    0.83
    nings
    0.79
     match
    0.77
    match
    0.76
     matches
    0.73
    ches
    0.69
    eering
    0.69
    ees
    0.68
    Activations Density 0.017%

    No Known Activations