© 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. 31009
    Prev
    Next
    INDEX
    Explanations

    terms related to dietary interventions and their effects on cholesterol levels

    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
    691
    +0.13
    0.6%
    357
    +0.10
    0.5%
    758
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    461
    +0.13
    0.05
    691
    +0.10
    0.06
    444
    +0.10
    0.05
    Negative Logits
     itch
    -0.69
     Lyme
    -0.69
    repair
    -0.68
    itability
    -0.67
     Carnage
    -0.67
     Borders
    -0.67
     cla
    -0.67
    thens
    -0.65
    rosis
    -0.65
    xiety
    -0.63
    POSITIVE LOGITS
     containing
    1.10
    containing
    1.09
     (%
    1.05
    ohydrate
    0.98
     products
    0.98
     fortified
    0.97
     beverages
    0.93
     âī¥
    0.91
     equivalents
    0.89
     intake
    0.87
    Activations Density 1.455%

    No Known Activations