© 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. 32713
    Prev
    Next
    INDEX
    Explanations

    topics related to conflicts, social divides, and political issues

    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
    +0.14
    0.6%
    37
    +0.10
    0.4%
    659
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.16
    67
    +0.10
    0.11
    365
    +0.10
    0.02
    Negative Logits
    pection
    -0.78
    ileaks
    -0.70
    acea
    -0.69
     Swordsman
    -0.64
     Frenchman
    -0.64
    odor
    -0.64
    eanor
    -0.64
    evidence
    -0.62
    name
    -0.62
    fecture
    -0.61
    POSITIVE LOGITS
     eras
    1.50
     regimes
    1.37
     universes
    1.27
     administrations
    1.26
     groups
    1.23
     periods
    1.22
     empires
    1.20
     budgets
    1.19
     populations
    1.19
     continents
    1.19
    Activations Density 2.994%

    No Known Activations