© 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. 27672
    Prev
    Next
    INDEX
    Explanations

    the word "of" in various 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
    101
    +0.13
    0.6%
    393
    +0.10
    0.4%
    157
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    101
    +0.13
    0.05
    362
    +0.10
    0.04
    322
    +0.09
    0.03
    Negative Logits
    EngineDebug
    -0.70
     manif
    -0.68
     encount
    -0.58
     endings
    -0.58
     outcomes
    -0.55
    arios
    -0.55
    ullivan
    -0.54
    jobs
    -0.53
    hya
    -0.53
    Tickets
    -0.53
    POSITIVE LOGITS
     Congress
    1.20
     Parliament
    1.16
     parliament
    1.13
     congress
    1.05
     society
    0.89
     staff
    0.86
     Pastebin
    0.85
     the
    0.77
     Anonymous
    0.73
     Team
    0.70
    Activations Density 0.263%

    No Known Activations