© 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. 32367
    Prev
    Next
    INDEX
    Explanations

    mentions of internal or related organizational matters, particularly within medical or governmental contexts

    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
    285
    +0.13
    0.6%
    288
    +0.11
    0.5%
    755
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    285
    +0.13
    0.02
    613
    +0.11
    0.01
    455
    +0.10
    0.02
    Negative Logits
    oÄŁ
    -0.79
    ensen
    -0.74
    enegger
    -0.73
    ammy
    -0.73
     Parables
    -0.72
    schild
    -0.71
    some
    -0.70
    uden
    -0.70
    ebook
    -0.70
    udeb
    -0.69
    POSITIVE LOGITS
     combustion
    1.27
    ized
    1.10
     workings
    1.07
    izing
    1.00
     affairs
    0.95
    ization
    0.92
    ised
    0.90
     organs
    0.88
    izable
    0.87
     strife
    0.84
    Activations Density 0.055%

    No Known Activations