© 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. 27004
    Prev
    Next
    INDEX
    Explanations

    closing parentheses in 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
    27
    +0.10
    0.5%
    388
    +0.10
    0.5%
    39
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    517
    +0.10
    0.04
    255
    +0.10
    0.05
    388
    +0.10
    0.05
    Negative Logits
    clus
    -0.66
     fid
    -0.65
     cogn
    -0.64
     aspir
    -0.62
     coron
    -0.61
    ibles
    -0.59
     heroine
    -0.59
     licensee
    -0.58
    ĪĴ
    -0.58
     monop
    -0.57
    POSITIVE LOGITS
    but
    1.06
     Otherwise
    0.98
     Anyway
    0.97
     Additionally
    0.96
     Also
    0.96
    while
    0.95
    because
    0.95
    until
    0.94
    and
    0.94
    then
    0.93
    Activations Density 0.455%

    No Known Activations