© 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 EvalsExportsAPI 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. 30733
    Prev
    Next
    INDEX
    Explanations

    references to "other" parties or groups in a context of comparison or contrast

    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
    393
    +0.14
    0.6%
    534
    +0.10
    0.4%
    408
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    319
    +0.14
    0.02
    534
    +0.10
    0.02
    153
    +0.09
    0.02
    Negative Logits
    veland
    -0.70
    ãĥĥ
    -0.68
    cale
    -0.68
     Shutterstock
    -0.67
    iste
    -0.67
    ategory
    -0.65
    ICO
    -0.65
    rogram
    -0.64
    zon
    -0.63
    wark
    -0.63
    POSITIVE LOGITS
    worldly
    1.70
     side
    1.10
     two
    1.02
     half
    1.02
     shoe
    0.90
     three
    0.90
     halves
    0.90
     364
    0.88
     installments
    0.87
     four
    0.84
    Activations Density 0.357%

    No Known Activations