© 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. 26224
    Prev
    Next
    INDEX
    Explanations

    issues related to parenting and child care practices

    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
    80
    +0.12
    0.5%
    46
    +0.11
    0.5%
    766
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.12
    0.09
    597
    +0.11
    0.08
    566
    +0.11
    0.08
    Negative Logits
    xon
    -0.73
     Vendor
    -0.69
     horizont
    -0.68
     Dealer
    -0.67
    izon
    -0.67
     creditor
    -0.66
    Universal
    -0.65
     Petroleum
    -0.64
     Restaur
    -0.62
    cation
    -0.61
    POSITIVE LOGITS
     children
    1.54
     youngsters
    1.37
     kids
    1.35
     infants
    1.35
    children
    1.34
     offspring
    1.29
     minors
    1.24
     toddlers
    1.23
     juveniles
    1.23
     babies
    1.20
    Activations Density 3.767%

    No Known Activations