© 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. 8-RES_POST_32K-OAI
    11. 6306
    Prev
    Next
    INDEX
    Explanations

    references to authors or organizations related to stem cell research and conferences

    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
    137
    +0.09
    0.4%
    14
    +0.09
    0.4%
    587
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    441
    +0.09
    0.04
    587
    +0.09
    0.05
    14
    +0.09
    0.04
    Negative Logits
    hedral
    -0.80
    ront
    -0.69
    orts
    -0.68
     resil
    -0.67
     helicop
    -0.66
    icum
    -0.66
     unnecess
    -0.65
    plot
    -0.65
    ovy
    -0.64
    ractions
    -0.63
    POSITIVE LOGITS
    -)
    1.19
    âĢ¢âĢ¢âĢ¢âĢ¢
    1.01
    âĢ¢âĢ¢
    0.91
     alternatively
    0.89
     thence
    0.82
     cf
    0.78
    alias
    0.77
    ////////
    0.75
     furthermore
    0.73
     consequently
    0.71
    Activations Density 0.242%

    No Known Activations