© 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. 26216
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical, scientific, or statistical functions and their relationships

    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
    716
    +0.10
    0.5%
    3
    +0.10
    0.5%
    592
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.10
    0.10
    252
    +0.10
    0.08
    756
    +0.09
    0.01
    Negative Logits
    issance
    -0.64
    uana
    -0.63
    iyah
    -0.60
    Cub
    -0.56
     Prison
    -0.55
     Louie
    -0.55
     Almighty
    -0.55
    é¾įå
    -0.55
     Barney
    -0.54
    Its
    -0.54
    POSITIVE LOGITS
     themselves
    0.92
     differently
    0.89
     respectively
    0.87
    ings
    0.86
     disproportionately
    0.82
     alike
    0.81
    ingly
    0.81
     similarly
    0.77
    selves
    0.70
    erent
    0.69
    Activations Density 2.140%

    No Known Activations