© 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. 7-RES-JB
    11. 23043
    Prev
    Next
    INDEX
    Explanations

    references to cricket matches and related terms, particularly focusing on the word "Test."

    oai_token-act-pair · gpt-3.5-turbo

    references to cricket matches, specifically "Test" matches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yg
    -0.82
    afort
    -0.80
    uyomi
    -0.72
    behavior
    -0.70
    anim
    -0.68
     sidewalks
    -0.68
     Canaver
    -0.67
    nown
    -0.66
    bart
    -0.66
    phal
    -0.65
    POSITIVE LOGITS
    osterone
    0.96
     cricket
    0.95
     opener
    0.92
     Rugby
    0.87
    imony
    0.86
     Championship
    0.80
     Championships
    0.78
     Series
    0.77
     Champions
    0.75
     unbeaten
    0.75
    Activations Density 0.045%

    No Known Activations