© 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. 8-RES_POST_32K-OAI
    11. 8809
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate provisions, support, or guidance for actions and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    314
    +0.13
    0.6%
    149
    +0.11
    0.5%
    581
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    97
    +0.13
    0.01
    309
    +0.11
    0.01
    711
    +0.11
    0.01
    Negative Logits
    Interstitial
    -0.77
     syll
    -0.67
    ospace
    -0.65
     diplom
    -0.65
    inders
    -0.64
     outnumbered
    -0.62
     wavelengths
    -0.62
     shel
    -0.62
     ultras
    -0.60
     aver
    -0.59
    POSITIVE LOGITS
    vice
    0.63
    Ĵ
    0.63
    pload
    0.60
    etz
    0.57
     whom
    0.57
    ĸ
    0.56
    App
    0.56
     PRO
    0.55
    ichen
    0.55
    ventures
    0.55
    Activations Density 0.063%

    No Known Activations