© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 32698
    Prev
    Next
    INDEX
    Explanations

    significant numerical data or dates related to events and publications

    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
    314
    +0.13
    0.6%
    638
    +0.12
    0.6%
    306
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    310
    +0.13
    0.07
    306
    +0.12
    0.06
    241
    +0.11
    0.05
    Negative Logits
     streng
    -0.79
     sugg
    -0.75
    avorite
    -0.67
     glim
    -0.65
    ufact
    -0.62
     gobl
    -0.61
     Genie
    -0.61
     gel
    -0.61
    chwitz
    -0.61
     advoc
    -0.61
    POSITIVE LOGITS
    th
    1.63
    ths
    1.05
    rd
    1.04
    teenth
    0.99
    TH
    0.99
    tha
    0.93
     2017
    0.82
     th
    0.81
     2018
    0.81
    st
    0.81
    Activations Density 0.237%

    No Known Activations