© 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 EvalsExportsinterp-engineNEWAPI 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. 28097
    Prev
    Next
    INDEX
    Explanations

    references to government-related entities and organizations

    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
    145
    +0.12
    0.5%
    466
    +0.10
    0.5%
    616
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.12
    0.16
    608
    +0.10
    0.13
    385
    +0.09
    0.12
    Negative Logits
    ãĤ¦ãĤ¹
    -0.87
     sanity
    -0.76
     ster
    -0.74
     wrinkles
    -0.73
    ocious
    -0.71
    ItemImage
    -0.70
     matters
    -0.67
    quickShipAvailable
    -0.66
     sails
    -0.65
     roar
    -0.65
    POSITIVE LOGITS
     government
    1.05
     Government
    1.04
     Department
    1.04
     governments
    0.97
     Centers
    0.95
     feds
    0.91
     Ministry
    0.88
     Treasury
    0.88
    government
    0.86
     federal
    0.86
    Activations Density 1.079%

    No Known Activations