© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 26206
    Prev
    Next
    INDEX
    Explanations

    the phrase structure "of" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    373
    +0.11
    0.5%
    564
    +0.10
    0.5%
    466
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.11
    0.04
    322
    +0.10
    0.04
    573
    +0.10
    0.03
    Negative Logits
    76561
    -0.70
    âĹ¼
    -0.68
    stellar
    -0.67
    EStreamFrame
    -0.66
    awaru
    -0.64
    seless
    -0.64
     timet
    -0.62
     behavi
    -0.62
    EXP
    -0.61
    attribute
    -0.61
    POSITIVE LOGITS
     Florida
    1.36
     Massachusetts
    1.36
     Maryland
    1.35
     Vermont
    1.32
     Rhode
    1.32
     Connecticut
    1.31
     Delaware
    1.29
     Illinois
    1.29
     California
    1.28
     Tennessee
    1.28
    Activations Density 0.263%

    No Known Activations