© 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. 26603
    Prev
    Next
    INDEX
    Explanations

    instances of the word "now" in various forms and contexts

    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
    283
    +0.14
    0.6%
    339
    +0.11
    0.5%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    683
    +0.14
    0.02
    267
    +0.11
    0.01
    339
    +0.10
    0.01
    Negative Logits
     enthusi
    -0.71
    é¾
    -0.70
     Berm
    -0.69
    tnc
    -0.69
    pmwiki
    -0.62
     Diesel
    -0.62
     merit
    -0.61
    natureconservancy
    -0.58
     elim
    -0.58
     Godzilla
    -0.57
    POSITIVE LOGITS
    adays
    1.48
    here
    1.26
    heres
    1.11
    rap
    1.00
    ledge
    0.96
    itz
    0.95
     Playing
    0.93
    Playing
    0.83
    ledged
    0.79
    ounce
    0.78
    Activations Density 0.080%

    No Known Activations