© 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. 10-RES_POST_32K-OAI
    11. 31557
    Prev
    Next
    INDEX
    Explanations

    references to email domains and organizational names

    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
    140
    +0.12
    0.5%
    257
    +0.11
    0.5%
    284
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    442
    +0.12
    0.03
    107
    +0.11
    0.03
    284
    +0.11
    0.02
    Negative Logits
     blurry
    -0.87
     metic
    -0.86
     smelling
    -0.82
     Pillar
    -0.81
     glim
    -0.76
     Rocks
    -0.75
     squirrel
    -0.72
     graz
    -0.71
     Runes
    -0.71
     fuzzy
    -0.71
    POSITIVE LOGITS
    com
    1.73
    edu
    1.34
    eu
    1.24
    mobi
    1.18
    wordpress
    1.17
    net
    1.17
    info
    1.17
    co
    1.17
    nz
    1.14
    COM
    1.13
    Activations Density 0.093%

    No Known Activations