© 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. 32696
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relationships or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    608
    +0.17
    0.8%
    669
    +0.14
    0.7%
    362
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.17
    0.10
    669
    +0.14
    0.08
    362
    +0.13
    0.07
    Negative Logits
    arta
    -0.68
    bishop
    -0.63
    dad
    -0.62
    mint
    -0.62
    >[
    -0.61
    ihad
    -0.61
    uria
    -0.61
    he
    -0.61
    iband
    -0.60
    Includes
    -0.60
    POSITIVE LOGITS
     other
    1.23
     others
    1.11
     what
    1.08
     previous
    0.95
     how
    0.90
     conventional
    0.89
     ordinary
    0.89
     typical
    0.86
     anything
    0.84
     those
    0.81
    Activations Density 0.610%

    No Known Activations