© 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. 26549
    Prev
    Next
    INDEX
    Explanations

    specific time intervals and numerical data

    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
    +0.13
    0.6%
    336
    +0.10
    0.5%
    530
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.13
    -0.02
    589
    +0.10
    0.01
    567
    +0.09
    0.01
    Negative Logits
    nce
    -0.74
    tc
    -0.66
    zl
    -0.65
    bley
    -0.64
    =/
    -0.64
     pse
    -0.63
    bane
    -0.62
     promot
    -0.61
    intosh
    -0.61
     visa
    -0.61
    POSITIVE LOGITS
    WAY
    0.65
     Lor
    0.64
     Wis
    0.63
     Andreas
    0.63
    ãĤ¢
    0.59
     Igor
    0.59
     Reck
    0.59
     Heroic
    0.57
    illi
    0.54
     Harrison
    0.54
    Activations Density 0.168%

    No Known Activations