© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8749
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving exponents

    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
    491
    +0.10
    0.4%
    326
    +0.09
    0.4%
    604
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.10
    0.03
    160
    +0.09
    0.03
    205
    +0.09
    0.02
    Negative Logits
    ias
    -0.78
    icio
    -0.71
    lain
    -0.70
    ividual
    -0.69
     aver
    -0.69
    oran
    -0.67
    iosis
    -0.66
    istically
    -0.66
    asar
    -0.65
     Pradesh
    -0.65
    POSITIVE LOGITS
    ^^^^
    1.02
    workshop
    0.75
    sin
    0.73
    DAY
    0.70
    ^^
    0.70
    Wi
    0.70
    Python
    0.70
    [[
    0.69
    christ
    0.68
    CN
    0.67
    Activations Density 0.082%

    No Known Activations