© 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. 28926
    Prev
    Next
    INDEX
    Explanations

    numerical data related to statistical or operational metrics

    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
    717
    +0.10
    0.5%
    32
    +0.10
    0.4%
    244
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    717
    +0.10
    0.09
    130
    +0.10
    0.05
    311
    +0.09
    0.01
    Negative Logits
    sembly
    -0.57
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.51
     skelet
    -0.50
    teenth
    -0.50
    soDeliveryDate
    -0.49
     behavi
    -0.46
     reconc
    -0.44
     disag
    -0.44
    actionDate
    -0.44
    riott
    -0.43
    POSITIVE LOGITS
    :
    2.27
    :(
    1.77
    :-
    1.76
    :[
    1.69
    .:
    1.69
    :"
    1.66
    :#
    1.64
    :,
    1.64
    :'
    1.62
    %:
    1.62
    Activations Density 4.289%

    No Known Activations