© 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. 8-RES_POST_32K-OAI
    11. 8483
    Prev
    Next
    INDEX
    Explanations

    function declarations and call syntax in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    720
    +0.11
    0.5%
    42
    +0.10
    0.5%
    753
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.11
    0.02
    132
    +0.10
    0.02
    493
    +0.10
    0.02
    Negative Logits
    lihood
    -0.81
     âĵĺ
    -0.70
    ridor
    -0.68
    ajo
    -0.66
     anyways
    -0.64
     squared
    -0.64
    ebook
    -0.64
    atown
    -0.62
    efficients
    -0.62
     anyway
    -0.60
    POSITIVE LOGITS
    artisan
    0.78
    PsyNetMessage
    0.67
    shake
    0.67
     {}
    0.60
    Lock
    0.60
    {"
    0.60
    sole
    0.59
    nil
    0.59
    izoph
    0.59
    yrinth
    0.58
    Activations Density 0.130%

    No Known Activations