© 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. 26258
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with versioning and measurements

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    314
    +0.11
    0.5%
    640
    +0.10
    0.5%
    284
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.11
    0.03
    137
    +0.10
    0.01
    640
    +0.09
    0.03
    Negative Logits
     affili
    -0.74
     refres
    -0.73
     indo
    -0.73
     ris
    -0.69
     archaeological
    -0.66
     coh
    -0.65
    gery
    -0.63
     smokes
    -0.63
     necks
    -0.63
    izoph
    -0.62
    POSITIVE LOGITS
    2017
    1.04
    2015
    1.03
    2016
    1.03
    2014
    1.01
    2013
    1.01
    dylib
    0.98
    2018
    0.98
    erb
    0.97
    2012
    0.96
    2011
    0.94
    Activations Density 0.223%

    No Known Activations