© 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. 31433
    Prev
    Next
    INDEX
    Explanations

    punctuation that indicates strong emotions or questions

    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
    640
    +0.14
    0.6%
    393
    +0.10
    0.5%
    391
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.14
    0.06
    232
    +0.10
    0.04
    267
    +0.10
    0.03
    Negative Logits
    )...
    -0.81
    Ļ½
    -0.80
    ),"
    -0.74
    entimes
    -0.72
     arsen
    -0.70
    withstanding
    -0.70
     reconc
    -0.69
     istg
    -0.69
    ).[
    -0.69
     fortunately
    -0.68
    POSITIVE LOGITS
     Euph
    0.80
     Retrieved
    0.72
    edu
    0.70
     Braun
    0.70
     Countdown
    0.70
     Reloaded
    0.69
     Seasons
    0.68
     Featuring
    0.68
    fm
    0.67
    com
    0.67
    Activations Density 0.206%

    No Known Activations