© 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. 26210
    Prev
    Next
    INDEX
    Explanations

    phrases indicating clarification and additional information

    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
    104
    +0.12
    0.6%
    274
    +0.12
    0.5%
    531
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.12
    0.08
    377
    +0.12
    0.08
    531
    +0.10
    0.07
    Negative Logits
    sbm
    -0.70
    urated
    -0.69
     diagrams
    -0.62
     EntityItem
    -0.57
    everal
    -0.57
    yles
    -0.57
    aden
    -0.57
     hemor
    -0.56
    ãĥı
    -0.55
     engulfed
    -0.55
    POSITIVE LOGITS
     tho
    0.92
     though
    0.92
    *:
    0.91
    !:
    0.88
     disclaimer
    0.82
    note
    0.80
    Anyway
    0.79
     caveat
    0.79
    Firstly
    0.79
     folks
    0.79
    Activations Density 0.746%

    No Known Activations