© 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. 26557
    Prev
    Next
    INDEX
    Explanations

    actions involving gestures or physical movements

    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
    526
    +0.10
    0.5%
    99
    +0.10
    0.5%
    756
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.10
    -0.00
    288
    +0.10
    0.03
    526
    +0.10
    0.00
    Negative Logits
     Berk
    -0.69
     Dish
    -0.67
     disadvant
    -0.64
    tin
    -0.63
     Jed
    -0.59
     Isles
    -0.59
     Pearl
    -0.58
     butt
    -0.58
    girl
    -0.58
     Boys
    -0.57
    POSITIVE LOGITS
    ured
    1.72
    uring
    1.55
    ures
    1.52
    urers
    1.47
    ure
    1.44
    ural
    1.40
    apo
    1.37
    urations
    1.35
    urer
    1.31
    URES
    1.28
    Activations Density 0.165%

    No Known Activations