© 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. 30649
    Prev
    Next
    INDEX
    Explanations

    the word "Sum" and its associated values indicating context related to measurements or summations

    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
    185
    +0.09
    0.4%
    621
    +0.09
    0.4%
    299
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.09
    0.03
    659
    +0.09
    0.02
    167
    +0.09
    0.00
    Negative Logits
    spection
    -0.76
    usive
    -0.74
    ãĥ©ãĥ³
    -0.73
    escription
    -0.65
    ãĥīãĥ©ãĤ´ãĥ³
    -0.65
    bery
    -0.63
    GGGGGGGG
    -0.62
    éĹĺ
    -0.61
    orage
    -0.61
    olate
    -0.61
    POSITIVE LOGITS
    NER
    0.78
    antha
    0.77
    ilk
    0.76
    arter
    0.75
    alon
    0.71
    an
    0.70
    icker
    0.69
    mill
    0.68
    istine
    0.63
     cliff
    0.62
    Activations Density 0.260%

    No Known Activations