© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 31736
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers and references within the text

    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
    373
    +0.17
    0.8%
    722
    +0.12
    0.5%
    96
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    655
    +0.17
    0.03
    96
    +0.12
    0.03
    488
    +0.11
    0.03
    Negative Logits
     Solitaire
    -0.78
     inheritance
    -0.72
    onite
    -0.62
    velt
    -0.59
     Pell
    -0.59
    erville
    -0.59
     kidding
    -0.58
    Maker
    -0.56
     epilepsy
    -0.56
     pouch
    -0.55
    POSITIVE LOGITS
    ii
    0.97
    iii
    0.94
    )].
    0.89
     largeDownload
    0.81
    «
    0.80
    â
    0.79
    )).
    0.78
    above
    0.76
    FIG
    0.76
    II
    0.74
    Activations Density 0.393%

    No Known Activations