© 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. 26403
    Prev
    Next
    INDEX
    Explanations

    positive sentiments about faith and inspirational experiences

    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
    8
    +0.11
    0.5%
    177
    +0.10
    0.5%
    327
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    177
    +0.11
    0.04
    672
    +0.10
    0.02
    183
    +0.10
    0.02
    Negative Logits
     Kardashian
    -1.09
    idas
    -0.99
    xual
    -0.90
     hairst
    -0.79
     creat
    -0.78
    Tile
    -0.77
    ç
    -0.75
     Farage
    -0.75
     Nike
    -0.75
     bikini
    -0.75
    POSITIVE LOGITS
    Reviewer
    1.19
     Grateful
    1.14
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    1.10
    Jerry
    1.06
     Jerry
    1.02
     Weir
    1.00
     Hartford
    0.92
     Garcia
    0.88
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    0.84
    ÃĥÃĤ
    0.83
    Activations Density 0.674%

    No Known Activations