© 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. 10-RES_POST_32K-OAI
    11. 28227
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming operations and dependencies

    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
    424
    +0.10
    0.5%
    356
    +0.09
    0.4%
    179
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.04
    755
    +0.09
    0.02
    362
    +0.09
    0.04
    Negative Logits
    vation
    -0.79
    emetery
    -0.73
    ï¸ı
    -0.72
    ometimes
    -0.70
    prototype
    -0.69
    Advertisements
    -0.69
    SPONSORED
    -0.68
    ricia
    -0.67
    DIV
    -0.67
    Leaks
    -0.66
    POSITIVE LOGITS
     pid
    0.91
     guid
    0.85
     '/
    0.81
     CLIENT
    0.76
     [-
    0.74
     CLSID
    0.70
     VK
    0.68
     config
    0.67
     [+]
    0.67
     PID
    0.65
    Activations Density 0.278%

    No Known Activations