© 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. 30240
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to individuals or entities associated with sports

    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
    385
    +0.10
    0.5%
    370
    +0.09
    0.4%
    404
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.10
    0.03
    406
    +0.09
    0.03
    404
    +0.09
    0.03
    Negative Logits
    herty
    -0.89
    kson
    -0.78
    soDeliveryDate
    -0.77
    RESULTS
    -0.72
     unbeliev
    -0.72
     IPM
    -0.65
    raction
    -0.65
    urized
    -0.63
     Tanz
    -0.63
    urations
    -0.62
    POSITIVE LOGITS
    naire
    1.56
    naires
    1.34
    aries
    1.20
    ary
    1.10
    ettes
    1.05
    ality
    0.99
    ucl
    0.96
    ists
    0.95
    ette
    0.94
    ist
    0.94
    Activations Density 0.395%

    No Known Activations