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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RES-JB
    6. 16259
    Prev
    Next
    INDEX
    Explanations

    references to Major League Soccer (MLS) and related terms

    oai_token-act-pair · gpt-3.5-turbo

    specific references to Major League Soccer (MLS) and its associated teams

    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
    enegger
    -0.83
     Norton
    -0.80
    iannopoulos
    -0.75
    debian
    -0.72
     Manson
    -0.70
    tops
    -0.69
    fman
    -0.68
    xus
    -0.66
    igslist
    -0.66
     charms
    -0.65
    POSITIVE LOGITS
    soc
    1.26
     Timbers
    1.12
     Soccer
    0.97
    FC
    0.96
     goalkeeper
    0.90
     Cup
    0.89
     Goal
    0.88
     MLS
    0.87
     Sounders
    0.84
    oos
    0.84
    Activations Density 0.048%

    No Known Activations