© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 8503
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports statistics, especially focusing on player performance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "for" indicating performance statistics

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

    No Comments

    Negative Logits
    mare
    -0.80
    sonian
    -0.75
    chwitz
    -0.74
    operated
    -0.71
    Introduced
    -0.71
    heart
    -0.70
    mun
    -0.69
    hess
    -0.69
    bil
    -0.68
    lein
    -0.67
    POSITIVE LOGITS
     starters
    1.07
    geries
    0.97
    aging
    0.97
     instance
    0.93
    bidden
    0.92
    ked
    0.87
    cing
    0.83
    gery
    0.82
     example
    0.82
     STATS
    0.81
    Activations Density 0.131%

    No Known Activations