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. 8-RES-JB
    6. 5892
    Prev
    Next
    INDEX
    Explanations

    sports statistics, rankings, and standings

    oai_token-act-pair · gpt-3.5-turbo

    numerical rankings or positions within various sports leagues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     breeze
    -0.70
    icer
    -0.69
    rod
    -0.68
     adjunct
    -0.66
    demon
    -0.66
    ream
    -0.65
    prototype
    -0.65
    qua
    -0.63
    wald
    -0.63
    abal
    -0.61
    POSITIVE LOGITS
     standings
    0.92
     rankings
    0.89
     Forbes
    0.87
     SPD
    0.79
     DV
    0.78
     overall
    0.77
     Adjusted
    0.74
     Nationwide
    0.71
     parentheses
    0.71
     Rankings
    0.71
    Activations Density 0.094%

    No Known Activations