© 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. 32645
    Prev
    Next
    INDEX
    Explanations

    references to charts, graphs, and data visualization elements

    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
    459
    +0.11
    0.5%
    555
    +0.10
    0.5%
    551
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.11
    -0.01
    192
    +0.10
    0.01
    546
    +0.09
    0.01
    Negative Logits
    saving
    -0.61
    ogical
    -0.61
    oresc
    -0.61
    llor
    -0.60
    enegger
    -0.60
     subscribing
    -0.59
    clave
    -0.58
    bringing
    -0.58
    azines
    -0.58
     conflicting
    -0.58
    POSITIVE LOGITS
    ickets
    0.66
    iah
    0.65
     Horus
    0.64
     Liang
    0.62
    ogens
    0.62
     Orleans
    0.61
    atar
    0.60
    dot
    0.57
     Pixie
    0.57
    irds
    0.57
    Activations Density 0.047%

    No Known Activations