© 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. 26193
    Prev
    Next
    INDEX
    Explanations

    numerical data, particularly counts or quantities

    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
    234
    +0.10
    0.4%
    253
    +0.09
    0.4%
    625
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    220
    +0.10
    0.10
    260
    +0.09
    0.09
    689
    +0.09
    0.07
    Negative Logits
    plus
    -0.80
    +)
    -0.74
     or
    -0.72
    +,
    -0.70
    apest
    -0.67
    to
    -0.66
    warts
    -0.66
    Or
    -0.63
    phis
    -0.62
    +
    -0.59
    POSITIVE LOGITS
    %.
    0.72
     years
    0.69
     sclerosis
    0.68
    %:
    0.63
     times
    0.62
     lbs
    0.62
    %"
    0.61
     thousands
    0.60
     folds
    0.58
     externalToEVAOnly
    0.58
    Activations Density 0.575%

    No Known Activations