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. 11-RES-JB
    6. 20101
    Prev
    Next
    INDEX
    Explanations

    text related to sports matches and players

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sports competitions and match outcomes

    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
     neighborhoods
    -0.89
    ı
    -0.84
    thumbnails
    -0.83
    uscript
    -0.78
     Medina
    -0.76
     neighborhood
    -0.76
     Eucl
    -0.75
     Neighborhood
    -0.73
    conom
    -0.73
     Erdogan
    -0.73
    POSITIVE LOGITS
     Rugby
    1.97
     rugby
    1.90
     NRL
    1.80
     Samoa
    1.62
     Fiji
    1.57
     Auckland
    1.54
    NZ
    1.52
     Kiw
    1.52
     Queensland
    1.50
     Ulster
    1.48
    Activations Density 0.390%

    No Known Activations