© 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. 8-RES_POST_32K-OAI
    11. 7521
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and their representations

    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
    400
    +0.10
    0.5%
    401
    +0.09
    0.4%
    228
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    503
    +0.10
    0.03
    570
    +0.09
    0.02
    364
    +0.09
    0.03
    Negative Logits
     Flo
    -0.74
    flo
    -0.65
    pill
    -0.63
     Paran
    -0.60
     imperson
    -0.60
    osc
    -0.60
     lawy
    -0.59
    minist
    -0.59
     linem
    -0.59
    epad
    -0.58
    POSITIVE LOGITS
     {
    1.79
    {
    1.65
     {*
    1.32
     {}
    1.27
     {"
    1.26
    {\
    1.22
     {\
    1.18
    {"
    1.18
     {:
    1.13
    {{
    1.09
    Activations Density 0.271%

    No Known Activations