© 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. 26349
    Prev
    Next
    INDEX
    Explanations

    references to historical dates and the concept of dating back

    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
    373
    +0.16
    0.7%
    327
    +0.12
    0.5%
    322
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    269
    +0.16
    0.05
    322
    +0.12
    0.05
    725
    +0.11
    0.04
    Negative Logits
    osed
    -0.70
    essen
    -0.69
    potion
    -0.68
    ims
    -0.68
    acs
    -0.63
    ressed
    -0.62
    resses
    -0.60
    renches
    -0.60
    osite
    -0.59
    ocal
    -0.59
    POSITIVE LOGITS
     infancy
    0.93
     earliest
    0.87
     before
    0.87
     antiquity
    0.85
     when
    0.82
     shortly
    0.78
     childhood
    0.78
    when
    0.78
     elementary
    0.77
     prehistoric
    0.72
    Activations Density 0.596%

    No Known Activations