© 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 EvalsExportsAPI 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. 6231
    Prev
    Next
    INDEX
    Explanations

    code structures and syntax elements commonly used in programming languages

    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
    472
    +0.12
    0.6%
    192
    +0.11
    0.5%
    593
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    558
    +0.12
    0.02
    700
    +0.11
    0.01
    593
    +0.09
    0.01
    Negative Logits
    anyahu
    -0.66
    vre
    -0.66
    benefit
    -0.66
    meaning
    -0.65
     corrid
    -0.64
    shapeshifter
    -0.64
     deserved
    -0.63
     outwe
    -0.63
    independence
    -0.63
    ãĥĥãĥī
    -0.62
    POSITIVE LOGITS
    ulia
    0.79
     //
    0.78
    console
    0.77
     Debug
    0.77
     Console
    0.75
    //
    0.70
     console
    0.69
     NG
    0.67
     var
    0.66
     Ensure
    0.65
    Activations Density 0.054%

    No Known Activations