© 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. 26194
    Prev
    Next
    INDEX
    Explanations

    structural elements in technical or mathematical contexts

    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
    334
    +0.12
    0.6%
    395
    +0.12
    0.5%
    107
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.12
    0.01
    284
    +0.12
    0.01
    107
    +0.12
    0.01
    Negative Logits
     lob
    -0.77
     eject
    -0.74
     cones
    -0.74
     framing
    -0.71
     boxed
    -0.70
     Divide
    -0.69
     subst
    -0.69
     ribs
    -0.67
     parentheses
    -0.67
     socket
    -0.67
    POSITIVE LOGITS
    Beta
    1.09
    VERSION
    1.01
    Versions
    0.98
    ç¥ŀ
    0.97
    beta
    0.94
    RIP
    0.92
    Alpha
    0.88
    Season
    0.88
    1
    0.88
    versions
    0.87
    Activations Density 0.041%

    No Known Activations