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. 0-RES-JB
    6. 17197
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Wimbledon"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific events or competitions, particularly in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uses
    -0.72
     ape
    -0.70
    adapt
    -0.69
    sat
    -0.66
    isol
    -0.63
     Kimber
    -0.62
     Tim
    -0.62
     Euph
    -0.62
     apes
    -0.62
     Gear
    -0.61
    POSITIVE LOGITS
    zag
    2.27
    bledon
    1.99
     diagonal
    1.56
    arella
    1.41
    fman
    1.35
    agall
    1.33
    avy
    1.33
    NN
    1.32
    andro
    1.23
    agonal
    1.19
    Activations Density 0.061%

    No Known Activations