© 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. 28032
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas and quotation marks

    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
    368
    +0.09
    0.4%
    456
    +0.09
    0.4%
    329
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    720
    +0.09
    0.06
    297
    +0.09
    0.05
    546
    +0.09
    0.05
    Negative Logits
    ²¾
    -0.86
    anmar
    -0.67
    heed
    -0.66
    ãĥ¼ãĥĨãĤ£
    -0.63
    worldly
    -0.63
    acas
    -0.62
    mares
    -0.62
     CoC
    -0.62
     sacrific
    -0.61
    etheless
    -0.61
    POSITIVE LOGITS
     referring
    0.95
    /"
    0.93
    [
    0.92
     meaning
    0.85
    {
    0.74
     implying
    0.72
    "[
    0.71
     i
    0.70
     according
    0.70
    meaning
    0.69
    Activations Density 0.476%

    No Known Activations