© 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. 31910
    Prev
    Next
    INDEX
    Explanations

    references to ratings or grading systems

    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
    641
    +0.11
    0.5%
    131
    +0.10
    0.5%
    465
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.05
    131
    +0.10
    0.03
    520
    +0.10
    0.04
    Negative Logits
    artifacts
    -0.87
    conserv
    -0.83
    ortium
    -0.82
    ilial
    -0.80
    adobe
    -0.78
    rises
    -0.78
    20439
    -0.77
    omnia
    -0.77
    DragonMagazine
    -0.77
    ":"","
    -0.77
    POSITIVE LOGITS
     Briggs
    0.74
     Hyde
    0.73
     Horton
    0.72
     Rutherford
    0.71
     Gillespie
    0.69
     Zam
    0.69
    .'
    0.67
     Roberts
    0.67
     Tolkien
    0.66
     Atkins
    0.66
    Activations Density 0.489%

    No Known Activations