© 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. 28621
    Prev
    Next
    INDEX
    Explanations

    phrases indicating predictions, assessments, or calculations about various 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
    279
    +0.11
    0.5%
    380
    +0.11
    0.5%
    262
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    479
    +0.11
    0.02
    375
    +0.11
    0.03
    669
    +0.10
    0.10
    Negative Logits
    actionDate
    -0.85
    NetMessage
    -0.77
    £ı
    -0.77
    maxwell
    -0.77
    yrim
    -0.76
    ciating
    -0.74
     Nir
    -0.73
     PAT
    -0.73
    Dar
    -0.71
     Levine
    -0.71
    POSITIVE LOGITS
     Bo
    1.73
    Mo
    1.70
     Mo
    1.69
    Ro
    1.68
     Ro
    1.68
    Bo
    1.59
    Ho
    1.57
     Ho
    1.57
     Lo
    1.54
     Fo
    1.52
    Activations Density 6.356%

    No Known Activations