© 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 EvalsExportsinterp-engineNEWAPI 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. 31847
    Prev
    Next
    INDEX
    Explanations

    topics related to medical advancements and regenerative therapies

    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
    429
    +0.11
    0.5%
    648
    +0.10
    0.4%
    501
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.11
    0.11
    308
    +0.10
    0.04
    145
    +0.10
    0.06
    Negative Logits
    ?),
    -0.79
    ),"
    -0.75
    unin
    -0.73
    ,)
    -0.70
    ,'"
    -0.68
    ?)
    -0.66
     Yun
    -0.66
    ?",
    -0.65
    quit
    -0.64
     Bulg
    -0.64
    POSITIVE LOGITS
     âĢ¢
    2.99
    âĢ¢
    2.73
    âĢ¢âĢ¢
    1.86
    »
    1.62
     âĸł
    1.61
     ÂŃ
    1.59
    âĸł
    1.59
     ·
    1.56
    âĢ¢âĢ¢âĢ¢âĢ¢
    1.55
     »
    1.54
    Activations Density 1.909%

    No Known Activations