© 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. 28617
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistical measures related to health conditions

    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
    290
    +0.12
    0.6%
    239
    +0.12
    0.6%
    469
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.12
    0.10
    194
    +0.12
    0.08
    145
    +0.11
    0.09
    Negative Logits
    soDeliveryDate
    -0.97
    pmwiki
    -0.89
    channelAvailability
    -0.87
     rake
    -0.79
     arrang
    -0.77
    redits
    -0.77
    etheless
    -0.77
     dilig
    -0.76
     ingred
    -0.75
    umbnails
    -0.74
    POSITIVE LOGITS
     âī¥
    1.24
     âī¤
    1.13
     âĪĴ
    1.11
     (%)
    1.06
     âĪ¼
    1.06
     Diabetes
    1.01
     (âĪĴ
    1.01
     Dietary
    1.01
    âĢł
    1.01
    §
    1.00
    Activations Density 0.596%

    No Known Activations