© 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 EvalsExportsAPI 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. 30290
    Prev
    Next
    INDEX
    Explanations

    references to beans and bean-related products

    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
    685
    +0.10
    0.5%
    36
    +0.10
    0.5%
    752
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.04
    659
    +0.10
    0.02
    326
    +0.10
    0.03
    Negative Logits
    illery
    -0.80
    acular
    -0.72
    Ö¼
    -0.68
    allas
    -0.66
    ongyang
    -0.65
    asury
    -0.64
    urai
    -0.63
     Seym
    -0.63
     glim
    -0.62
    nces
    -0.61
    POSITIVE LOGITS
    ie
    0.99
    bean
    0.88
    beans
    0.79
    bags
    0.77
    seed
    0.76
    essa
    0.74
    let
    0.73
     spr
    0.72
    bag
    0.71
    quer
    0.71
    Activations Density 0.223%

    No Known Activations