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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 13910
    Prev
    Next
    INDEX
    Explanations

    terms related to sports events, particularly World Championships and World Cups

    oai_token-act-pair · gpt-3.5-turbo

    references to "World" events, specifically championships or cups

    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
    fman
    -0.74
    netflix
    -0.72
    nyder
    -0.71
    clinton
    -0.71
    rss
    -0.71
     inertia
    -0.69
    nces
    -0.67
    aturday
    -0.66
    dq
    -0.66
    ments
    -0.65
    POSITIVE LOGITS
     Championships
    1.40
     Championship
    1.31
     Cup
    1.27
     Series
    1.21
    Tour
    1.17
     Cups
    1.07
     Finals
    1.03
     championships
    0.99
     championship
    0.97
     Rankings
    0.97
    Activations Density 0.025%

    No Known Activations