© 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. 26246
    Prev
    Next
    INDEX
    Explanations

    references to same-sex marriage and public opinion on it

    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
    +0.14
    0.6%
    151
    +0.09
    0.4%
    468
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    162
    +0.14
    0.01
    694
    +0.09
    0.01
    425
    +0.09
    0.01
    Negative Logits
     Kham
    -0.71
     Belg
    -0.63
     Canaver
    -0.62
     Lama
    -0.61
     Roundup
    -0.61
    ahime
    -0.61
     Utt
    -0.61
     Kash
    -0.60
     Idlib
    -0.59
     Olympia
    -0.58
    POSITIVE LOGITS
    sex
    1.08
    Sex
    1.03
     sex
    1.02
    vi
    0.86
    gender
    0.80
    -
    0.79
     Sex
    0.78
    âĢIJ
    0.77
     sexes
    0.77
    -(
    0.75
    Activations Density 0.118%

    No Known Activations