© 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. 29596
    Prev
    Next
    INDEX
    Explanations

    geographical locations or place names

    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
    373
    +0.19
    0.9%
    383
    +0.10
    0.5%
    613
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    380
    +0.19
    0.04
    530
    +0.10
    0.05
    329
    +0.10
    0.04
    Negative Logits
    DragonMagazine
    -0.84
     Restaur
    -0.71
    irin
    -0.71
     balcon
    -0.69
    arin
    -0.68
    abouts
    -0.67
    cair
    -0.64
    /+
    -0.62
    ãĤ³
    -0.62
     sunset
    -0.61
    POSITIVE LOGITS
     Connecticut
    0.93
     Berkshire
    0.93
     Massachusetts
    0.88
     Kentucky
    0.83
     Berks
    0.78
     Virginia
    0.78
     Michigan
    0.75
     Pennsylvania
    0.74
     Delaware
    0.73
     West
    0.73
    Activations Density 0.496%

    No Known Activations