© 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. 26230
    Prev
    Next
    INDEX
    Explanations

    references to polling data and surveys

    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
    373
    +0.11
    0.5%
    345
    +0.10
    0.4%
    690
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    508
    +0.11
    0.04
    683
    +0.10
    0.05
    346
    +0.09
    0.05
    Negative Logits
     Canaver
    -0.77
    imov
    -0.72
     forgiven
    -0.72
     salts
    -0.68
    udicrous
    -0.67
     vest
    -0.65
     healer
    -0.65
     apologise
    -0.64
    oshenko
    -0.64
     apologised
    -0.64
    POSITIVE LOGITS
     survey
    1.13
     poll
    1.11
     Poll
    0.96
    Poll
    0.96
     Survey
    0.90
     study
    0.86
    itudinal
    0.86
    aukee
    0.84
     Religion
    0.83
    Economic
    0.82
    Activations Density 0.688%

    No Known Activations