© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 29790
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and LaTeX formatting related to matrices

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    442
    +0.10
    0.4%
    575
    +0.09
    0.4%
    678
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.10
    0.07
    107
    +0.09
    0.06
    699
    +0.09
    0.05
    Negative Logits
     Pigs
    -0.84
     IPM
    -0.83
     Therapy
    -0.74
     futures
    -0.71
     Viv
    -0.69
     Jericho
    -0.69
     Practices
    -0.67
     Ara
    -0.67
     workshops
    -0.66
     Nets
    -0.66
    POSITIVE LOGITS
    margin
    1.02
    ĸļ
    0.99
    end
    0.98
    Ń
    0.92
    upper
    0.91
    frac
    0.90
    Msg
    0.89
    begin
    0.89
    color
    0.88
    ell
    0.87
    Activations Density 0.340%

    No Known Activations