© 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. 8891
    Prev
    Next
    INDEX
    Explanations

    instances of the word "or" suggesting alternatives or options

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    709
    +0.14
    0.6%
    639
    +0.09
    0.4%
    120
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    596
    +0.14
    0.03
    236
    +0.09
    0.04
    763
    +0.09
    0.03
    Negative Logits
    "],
    -0.72
    ADE
    -0.72
    tree
    -0.69
    "],"
    -0.66
    sb
    -0.65
    haus
    -0.65
    BACK
    -0.60
    phthal
    -0.59
    iji
    -0.59
    VERS
    -0.59
    POSITIVE LOGITS
    withstanding
    0.99
     optionally
    0.94
     possibly
    0.85
     indeed
    0.83
     ideally
    0.81
    respective
    0.81
     preferably
    0.79
    selves
    0.79
    etheless
    0.77
     vice
    0.74
    Activations Density 0.208%

    No Known Activations