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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4270
    Prev
    Next
    INDEX
    Explanations

    references to the Seattle Sounders soccer team

    oai_token-act-pair · gpt-3.5-turbo

    references to sports teams, particularly in relation to 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
    ously
    -0.84
    enegger
    -0.74
    EVA
    -0.73
    esty
    -0.71
    erala
    -0.70
    bart
    -0.69
    axter
    -0.69
    elsen
    -0.68
    trak
    -0.68
    fecture
    -0.67
    POSITIVE LOGITS
     Timbers
    1.45
     Sounders
    1.24
     Earthqu
    1.02
     Soccer
    0.99
     FC
    0.96
     Dynamo
    0.94
     MLS
    0.89
     Hots
    0.86
     Supporters
    0.86
     Jagu
    0.85
    Activations Density 0.021%

    No Known Activations