© 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. 31333
    Prev
    Next
    INDEX
    Explanations

    elements related to mathematical plotting and graphing in data visualization

    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
    756
    +0.14
    0.6%
    54
    +0.13
    0.6%
    598
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.06
    678
    +0.13
    0.04
    738
    +0.10
    0.03
    Negative Logits
     Bombay
    -0.93
     Sharma
    -0.88
     fragmentation
    -0.87
     Palest
    -0.87
     Spectre
    -0.85
     JPM
    -0.81
     Amit
    -0.80
     Mumbai
    -0.80
     Jericho
    -0.77
     Dh
    -0.77
    POSITIVE LOGITS
    @#&
    1.61
     \"
    1.52
    )!
    1.22
    !
    1.00
    \"
    0.91
    local
    0.85
    ¢
    0.82
    !!
    0.82
    !"
    0.79
    =\"
    0.78
    Activations Density 0.269%

    No Known Activations