© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 26383
    Prev
    Next
    INDEX
    Explanations

    specific numerical data or statistical information

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    443
    +0.11
    0.5%
    722
    +0.10
    0.5%
    596
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.11
    -0.12
    31
    +0.10
    0.07
    426
    +0.10
    0.04
    Negative Logits
     Tak
    -1.05
     Tav
    -1.05
     KH
    -0.99
    FK
    -0.94
     Ott
    -0.93
     Kak
    -0.90
    atan
    -0.86
    ohan
    -0.85
     Kahn
    -0.83
     Oswald
    -0.83
    POSITIVE LOGITS
    29
    1.22
     290
    1.17
     29
    1.17
    290
    1.16
     291
    1.15
    293
    1.14
     295
    1.12
    291
    1.12
     289
    1.12
     294
    1.11
    Activations Density 5.906%

    No Known Activations