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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 29509
    Prev
    Next
    INDEX
    Explanations

    items related to player statistics or performance in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    309
    +0.11
    0.5%
    505
    +0.11
    0.5%
    429
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    241
    +0.11
    0.02
    702
    +0.11
    0.02
    601
    +0.10
    0.01
    Negative Logits
     Nun
    -0.73
    uberty
    -0.70
    polit
    -0.66
    enegger
    -0.63
    istor
    -0.63
     Belg
    -0.63
    anmar
    -0.63
    >[
    -0.62
     1862
    -0.61
    /,
    -0.61
    POSITIVE LOGITS
     Playoffs
    0.97
     postseason
    0.95
     Rookie
    0.95
     Yankees
    0.90
     playoff
    0.88
     playoffs
    0.88
     Lakers
    0.87
     Knicks
    0.87
     Cardinals
    0.85
     Timberwolves
    0.85
    Activations Density 0.143%

    No Known Activations