© 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. 30941
    Prev
    Next
    INDEX
    Explanations

    file paths and directories commonly used in system environments

    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
    314
    +0.12
    0.6%
    393
    +0.12
    0.6%
    107
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    365
    +0.12
    0.02
    102
    +0.12
    0.04
    160
    +0.10
    0.04
    Negative Logits
     Courage
    -0.87
     Satanic
    -0.78
     Coil
    -0.76
     Emmy
    -0.75
     Thrones
    -0.73
     Phi
    -0.72
     Percy
    -0.72
     Cotton
    -0.71
     Rounds
    -0.70
     Spike
    -0.70
    POSITIVE LOGITS
    cdn
    1.32
    sd
    1.28
    tools
    1.21
    manager
    1.19
    usa
    1.17
    linux
    1.17
    server
    1.17
    api
    1.15
    setup
    1.14
    settings
    1.12
    Activations Density 0.189%

    No Known Activations