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. 1-RES-JB
    6. 18425
    Prev
    Next
    INDEX
    Explanations

    words related to soccer

    oai_token-act-pair · gpt-3.5-turbo

    references to the sport of soccer

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ++++++++++++++++
    -0.70
     Ples
    -0.69
    enment
    -0.68
    ysis
    -0.67
    ogen
    -0.66
    nces
    -0.66
     miscar
    -0.64
    å§«
    -0.63
    urat
    -0.63
    vae
    -0.62
    POSITIVE LOGITS
     soccer
    1.34
     Soccer
    0.99
     academy
    0.89
    soc
    0.87
     goalie
    0.85
     stadium
    0.83
     stadiums
    0.83
     acad
    0.80
    istani
    0.80
     volleyball
    0.79
    Activations Density 0.008%

    No Known Activations