© 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. 26487
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas and periods

    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
    4
    +0.16
    0.7%
    314
    +0.11
    0.5%
    177
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    720
    +0.16
    0.14
    297
    +0.11
    0.11
    546
    +0.09
    0.09
    Negative Logits
     hereafter
    -0.75
    ĸļ
    -0.65
    entimes
    -0.63
     condu
    -0.63
     Compare
    -0.62
     Compar
    -0.61
    FactoryReloaded
    -0.61
    depending
    -0.60
     respectively
    -0.60
    ogether
    -0.60
    POSITIVE LOGITS
     grabbed
    0.94
     clutching
    0.86
     boarded
    0.86
     hopped
    0.84
     bowed
    0.81
     handcuffs
    0.81
     unsc
    0.80
     climbed
    0.80
     exhausted
    0.80
     hugged
    0.78
    Activations Density 1.478%

    No Known Activations