© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 29658
    Prev
    Next
    INDEX
    Explanations

    numerical values and various symbols that appear frequently in mathematical or programming contexts

    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
    341
    +0.11
    0.5%
    258
    +0.11
    0.5%
    173
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.11
    0.05
    232
    +0.11
    0.11
    731
    +0.10
    0.02
    Negative Logits
     Ply
    -0.91
     Jinn
    -0.77
    WF
    -0.77
     Winston
    -0.75
     Neptune
    -0.71
     Reynolds
    -0.70
     Kling
    -0.69
    Wil
    -0.69
     Kol
    -0.68
    worm
    -0.67
    POSITIVE LOGITS
    AA
    1.06
    AG
    1.04
    AC
    1.00
     Ao
    0.97
     Ap
    0.97
    ATA
    0.96
     Ai
    0.95
     Aad
    0.95
    atar
    0.94
     Ara
    0.94
    Activations Density 9.573%

    No Known Activations