© 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. 4295
    Prev
    Next
    INDEX
    Explanations

    Spanish words and phrases indicating relationships or connections

    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
    521
    +0.12
    0.6%
    756
    +0.12
    0.5%
    672
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.07
    284
    +0.12
    0.06
    232
    +0.11
    0.06
    Negative Logits
     defect
    -0.58
    %"
    -0.58
    itiveness
    -0.57
    yip
    -0.56
     Krug
    -0.56
    orders
    -0.55
    osterone
    -0.55
     axes
    -0.55
    ggles
    -0.55
    assetsadobe
    -0.54
    POSITIVE LOGITS
    etus
    1.05
    orius
    0.69
    esi
    0.68
    ito
    0.68
    warm
    0.67
    FUL
    0.65
    Ħ¢
    0.64
    onen
    0.63
    idy
    0.61
    ¦
    0.60
    Activations Density 1.166%

    No Known Activations