© 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. 32640
    Prev
    Next
    INDEX
    Explanations

    geographic locations and descriptions of borders

    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
    435
    +0.11
    0.5%
    559
    +0.10
    0.5%
    180
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    761
    +0.11
    0.07
    154
    +0.10
    0.07
    677
    +0.10
    0.06
    Negative Logits
     tenants
    -0.80
    ODY
    -0.77
    amily
    -0.75
     residences
    -0.75
     upbringing
    -0.75
     homeowners
    -0.74
     classrooms
    -0.73
     studios
    -0.72
    housing
    -0.72
    thood
    -0.71
    POSITIVE LOGITS
     Euph
    1.29
    border
    1.01
     Strait
    0.99
     Nile
    0.96
     Stra
    0.96
     Mediterranean
    0.95
     border
    0.95
     River
    0.94
     Tig
    0.93
     river
    0.93
    Activations Density 1.567%

    No Known Activations