© 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. 26197
    Prev
    Next
    INDEX
    Explanations

    references to government officials and ministries

    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
    288
    +0.15
    0.7%
    437
    +0.12
    0.5%
    314
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    238
    +0.15
    0.03
    224
    +0.12
    0.03
    146
    +0.11
    0.03
    Negative Logits
    vent
    -0.69
    schild
    -0.67
     Fres
    -0.65
     Samurai
    -0.63
     Nation
    -0.61
     Asgard
    -0.60
     Colossus
    -0.60
     Savior
    -0.59
     Detected
    -0.59
     WAR
    -0.58
    POSITIVE LOGITS
    ial
    1.16
    arians
    1.00
    arian
    0.94
    onse
    0.90
    ials
    0.88
    istry
    0.86
    isms
    0.84
    ister
    0.83
    alties
    0.80
    ially
    0.80
    Activations Density 0.129%

    No Known Activations