© 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. 8-RES_POST_32K-OAI
    11. 5545
    Prev
    Next
    INDEX
    Explanations

    references to the gender distribution of men and women

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    314
    +0.12
    0.6%
    363
    +0.10
    0.5%
    274
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    363
    +0.12
    0.05
    639
    +0.10
    0.04
    393
    +0.08
    0.05
    Negative Logits
    inventoryQuantity
    -0.66
     cancellation
    -0.65
     withdrawals
    -0.63
    umi
    -0.63
    URR
    -0.62
    BIP
    -0.62
    advertisement
    -0.60
    Series
    -0.60
    Bonus
    -0.60
     withdrawal
    -0.60
    POSITIVE LOGITS
     woman
    1.13
     women
    1.07
     WOM
    1.06
     Woman
    1.00
    woman
    0.97
    women
    0.96
    Women
    0.93
    boys
    0.91
    Woman
    0.91
     Women
    0.90
    Activations Density 0.713%

    No Known Activations