© 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 EvalsExportsAPI 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. 30386
    Prev
    Next
    INDEX
    Explanations

    key terms related to international relations, particularly alliances and partnerships

    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
    154
    +0.13
    0.6%
    28
    +0.11
    0.5%
    249
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    154
    +0.13
    0.12
    249
    +0.11
    0.05
    756
    +0.10
    0.00
    Negative Logits
    summary
    -0.75
     Werewolf
    -0.75
     Reverend
    -0.75
    EVA
    -0.72
     Seconds
    -0.71
    assion
    -0.71
    alloween
    -0.71
     Explain
    -0.70
     Inquiry
    -0.70
    rompt
    -0.69
    POSITIVE LOGITS
     hegemony
    1.12
     strategic
    1.05
     geopolitical
    1.02
     clout
    1.02
     strategically
    0.99
     foothold
    0.98
     leverage
    0.97
     dominance
    0.97
     petroleum
    0.95
     geop
    0.95
    Activations Density 3.996%

    No Known Activations