© 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. 26214
    Prev
    Next
    INDEX
    Explanations

    geographic locations and associated regions

    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
    34
    +0.12
    0.5%
    685
    +0.11
    0.5%
    236
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    530
    +0.12
    0.06
    236
    +0.11
    0.06
    398
    +0.10
    0.04
    Negative Logits
    elsen
    -0.70
    ardless
    -0.66
     ponies
    -0.65
     Winchester
    -0.64
    Mayor
    -0.64
    mons
    -0.64
    zzle
    -0.63
    unicip
    -0.63
     pony
    -0.63
    NRS
    -0.61
    POSITIVE LOGITS
     Asia
    1.49
     Africa
    1.39
     Euras
    1.36
     Austral
    1.33
     Americas
    1.30
    Asia
    1.29
     Latin
    1.25
     Caribbean
    1.22
     Balkans
    1.17
     Southeast
    1.16
    Activations Density 1.108%

    No Known Activations