© 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. 26479
    Prev
    Next
    INDEX
    Explanations

    phrases indicating variability and uncertainty in timeframes or durations

    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
    678
    +0.11
    0.5%
    676
    +0.11
    0.5%
    238
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.11
    0.05
    238
    +0.11
    0.03
    393
    +0.10
    0.06
    Negative Logits
     Hood
    -0.78
    ãĤ¨
    -0.66
    ORY
    -0.66
    BACK
    -0.63
     Recreation
    -0.62
    arts
    -0.61
    BIL
    -0.61
    cohol
    -0.61
     Reconstruction
    -0.59
    ANC
    -0.59
    POSITIVE LOGITS
     weeks
    1.05
     months
    1.01
    years
    1.01
     milliseconds
    1.00
    months
    1.00
     years
    1.00
     seconds
    0.99
     thirds
    0.95
     centuries
    0.95
     inches
    0.94
    Activations Density 0.596%

    No Known Activations