© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 29653
    Prev
    Next
    INDEX
    Explanations

    references to routing and route definitions within a programming context

    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
    515
    +0.10
    0.5%
    445
    +0.10
    0.5%
    130
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.10
    0.02
    288
    +0.10
    0.02
    255
    +0.10
    0.02
    Negative Logits
    uster
    -0.83
    luaj
    -0.81
    oice
    -0.75
    usters
    -0.71
    merce
    -0.69
    iations
    -0.69
    iating
    -0.69
    minster
    -0.69
    untu
    -0.69
    ternity
    -0.69
    POSITIVE LOGITS
    finding
    1.07
    finder
    0.92
     routes
    0.89
    book
    0.86
    route
    0.84
    WAYS
    0.80
    ãĥ¼ãĥ³
    0.78
    Route
    0.77
     route
    0.77
    WAY
    0.73
    Activations Density 0.065%

    No Known Activations