© 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. 26769
    Prev
    Next
    INDEX
    Explanations

    various types of punctuation and formatting characters

    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
    618
    +0.10
    0.5%
    326
    +0.10
    0.4%
    263
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.10
    0.05
    160
    +0.10
    0.05
    627
    +0.09
    0.01
    Negative Logits
     poaching
    -0.75
    yip
    -0.73
     parting
    -0.69
     volunt
    -0.68
    uliffe
    -0.68
     subsistence
    -0.68
     dispers
    -0.67
     quantitative
    -0.67
     moder
    -0.66
     dipping
    -0.66
    POSITIVE LOGITS
    cv
    1.02
    1945
    0.99
    03
    0.97
    MSN
    0.95
    364
    0.95
    2003
    0.93
    1991
    0.93
    2011
    0.93
    2002
    0.92
    2004
    0.91
    Activations Density 0.392%

    No Known Activations