© 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. 8751
    Prev
    Next
    INDEX
    Explanations

    proper nouns and titles related to specific entities or events

    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
    374
    +0.10
    0.5%
    155
    +0.10
    0.4%
    463
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.01
    194
    +0.10
    0.01
    314
    +0.09
    -0.00
    Negative Logits
    terday
    -0.91
    ILE
    -0.81
    abwe
    -0.77
    cair
    -0.76
    neau
    -0.71
    tesy
    -0.70
    ibly
    -0.69
    bda
    -0.68
    vironment
    -0.68
    fw
    -0.67
    POSITIVE LOGITS
     Majesty
    0.70
     Leviathan
    0.60
     Mystery
    0.58
     redeem
    0.58
     nem
    0.56
     Escape
    0.56
     deductible
    0.56
     Worst
    0.55
    inion
    0.55
     Ruler
    0.54
    Activations Density 0.018%

    No Known Activations