© 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. 26441
    Prev
    Next
    INDEX
    Explanations

    the word "as" 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
    683
    +0.10
    0.5%
    218
    +0.10
    0.5%
    525
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    441
    +0.10
    0.03
    218
    +0.10
    0.03
    192
    +0.10
    0.03
    Negative Logits
    Downloadha
    -0.68
    ãĤ´ãĥ³
    -0.67
    ndum
    -0.66
    soDeliveryDate
    -0.65
     Named
    -0.64
    clus
    -0.64
     fue
    -0.62
    trop
    -0.61
    iterranean
    -0.60
    luaj
    -0.59
    POSITIVE LOGITS
     if
    0.95
     though
    0.81
     bullets
    0.77
     tears
    0.73
    soever
    0.72
    ethy
    0.69
    ami
    0.67
    hiro
    0.67
     footsteps
    0.65
     she
    0.64
    Activations Density 0.102%

    No Known Activations