Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 16188
    Prev
    Next
    INDEX
    Explanations

    sports-related events, specifically plays and actions during games

    oai_token-act-pair · gpt-3.5-turbo

    references to sports game phases and scoring events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    netflix
    -0.86
    enegger
    -0.85
    indust
    -0.75
    kefeller
    -0.74
    onym
    -0.72
     heirs
    -0.69
    ersive
    -0.69
    VW
    -0.69
    chwitz
    -0.68
     Canaver
    -0.67
    POSITIVE LOGITS
     halftime
    1.08
     timeout
    1.05
     inning
    0.97
     replay
    0.92
     innings
    0.90
    mination
    0.87
     opener
    0.87
     scrimmage
    0.86
     scoreboard
    0.85
     minute
    0.82
    Activations Density 0.256%

    No Known Activations