© 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. 26518
    Prev
    Next
    INDEX
    Explanations

    numerical data and values

    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
    295
    +0.09
    0.4%
    462
    +0.09
    0.4%
    502
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    503
    +0.09
    0.00
    334
    +0.09
    0.01
    90
    +0.09
    0.02
    Negative Logits
    tein
    -0.87
     spons
    -0.84
    etsk
    -0.75
    ngth
    -0.74
    uyomi
    -0.68
    enhagen
    -0.66
     scales
    -0.66
    DonaldTrump
    -0.65
     detrim
    -0.63
    soDeliveryDate
    -0.61
    POSITIVE LOGITS
    00
    1.17
    000
    0.80
    ight
    0.78
    olog
    0.71
    noon
    0.70
    30
    0.69
    50
    0.68
     CET
    0.65
    GMT
    0.65
    100
    0.65
    Activations Density 0.143%

    No Known Activations