© 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. 26295
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to programming and data structures

    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
    255
    +0.15
    0.7%
    668
    +0.10
    0.5%
    256
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.15
    0.18
    255
    +0.10
    0.17
    87
    +0.10
    -0.10
    Negative Logits
     Maur
    -0.75
     Brent
    -0.75
     Willie
    -0.73
     Hanson
    -0.72
     Benedict
    -0.72
     Dane
    -0.71
     Campbell
    -0.71
     Bett
    -0.71
     Nev
    -0.71
     Everett
    -0.71
    POSITIVE LOGITS
     initialization
    1.20
     parameter
    1.18
     config
    1.18
     overwrite
    1.15
     configure
    1.15
     integer
    1.12
     HTTP
    1.12
    HTTP
    1.12
    Config
    1.12
     executable
    1.11
    Activations Density 3.752%

    No Known Activations