© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 4714
    Prev
    Next
    INDEX
    Explanations

    references to data, measurements, or statistics related to specific subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    373
    +0.12
    0.5%
    293
    +0.10
    0.5%
    419
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.11
    317
    +0.10
    0.10
    667
    +0.10
    0.06
    Negative Logits
     Vand
    -0.75
     Joan
    -0.72
    anni
    -0.69
     Farage
    -0.68
     sprung
    -0.68
     Ying
    -0.67
    rick
    -0.67
    iton
    -0.67
     sund
    -0.66
     Fulton
    -0.66
    POSITIVE LOGITS
    iol
    0.91
    Į
    0.86
    aez
    0.84
    ocol
    0.83
    IO
    0.80
    io
    0.77
    EW
    0.75
    erv
    0.74
    eez
    0.73
    mol
    0.73
    Activations Density 2.693%

    No Known Activations