© 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. 32740
    Prev
    Next
    INDEX
    Explanations

    specific punctuation marks and certain grammatical structures

    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
    684
    +0.10
    0.5%
    118
    +0.09
    0.4%
    757
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    412
    +0.10
    0.01
    637
    +0.09
    0.01
    497
    +0.09
    0.00
    Negative Logits
    aan
    -0.74
    £ı
    -0.68
    alos
    -0.67
    uscript
    -0.66
    terness
    -0.65
    ĪĴ
    -0.64
    pmwiki
    -0.64
    «ĺ
    -0.63
    isons
    -0.63
     nomine
    -0.63
    POSITIVE LOGITS
     Cost
    0.89
     Also
    0.74
     Similarly
    0.68
    raine
    0.67
     Other
    0.64
     Each
    0.64
     Pant
    0.63
    soDeliveryDate
    0.63
    dds
    0.62
     Likewise
    0.62
    Activations Density 0.231%

    No Known Activations