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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 29213
    Prev
    Next
    INDEX
    Explanations

    repeated mentions or emphasis on specific key performance metrics or player contributions 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
    429
    +0.12
    0.6%
    583
    +0.12
    0.6%
    338
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.12
    0.16
    539
    +0.12
    0.15
    143
    +0.10
    0.15
    Negative Logits
    SPONSORED
    -0.98
     holiest
    -0.83
    ndra
    -0.81
    Virgin
    -0.78
     Nath
    -0.74
     UNESCO
    -0.68
     Transgender
    -0.67
    alian
    -0.66
     Norn
    -0.66
     Siren
    -0.65
    POSITIVE LOGITS
     FANTASY
    0.96
    orld
    0.95
    Thumbnail
    0.82
     coaching
    0.81
     offseason
    0.81
     coached
    0.79
     quarterback
    0.79
     coaches
    0.78
    Coach
    0.77
     locker
    0.76
    Activations Density 1.816%

    No Known Activations