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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 31978
    Prev
    Next
    INDEX
    Explanations

    connections and relationships between countries, particularly with reference to geopolitical dynamics

    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
    322
    +0.10
    0.5%
    473
    +0.10
    0.4%
    760
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.10
    0.11
    362
    +0.10
    0.09
    608
    +0.09
    0.10
    Negative Logits
    oru
    -0.80
    rotein
    -0.78
    ovi
    -0.72
     Jav
    -0.71
    quin
    -0.71
     INV
    -0.70
    Lev
    -0.69
    rament
    -0.68
    milo
    -0.68
    ov
    -0.67
    POSITIVE LOGITS
     separatists
    0.77
     Ukraine
    0.74
     Belarus
    0.74
     Crimea
    0.73
     Alibaba
    0.73
     Gaul
    0.73
     Bundesliga
    0.72
     Ukrainians
    0.70
    imaru
    0.66
     Angela
    0.66
    Activations Density 2.060%

    No Known Activations