© 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. 27280
    Prev
    Next
    INDEX
    Explanations

    statistical data and percentages

    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
    314
    +0.11
    0.5%
    16
    +0.10
    0.5%
    506
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.11
    -0.01
    284
    +0.10
    0.03
    176
    +0.10
    0.01
    Negative Logits
     oun
    -0.81
     proble
    -0.78
     certific
    -0.73
     neighb
    -0.69
     soph
    -0.67
     fuzzy
    -0.66
     accomp
    -0.65
     resid
    -0.65
     princ
    -0.65
     newsp
    -0.64
    POSITIVE LOGITS
    %
    2.09
    %.
    1.56
    %,
    1.55
    %-
    1.39
    %"
    1.38
    %;
    1.35
    %)
    1.29
    %).
    1.23
    %),
    1.23
    \">
    1.17
    Activations Density 0.271%

    No Known Activations