© 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. 26199
    Prev
    Next
    INDEX
    Explanations

    variations of the word "par" in different contexts

    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
    620
    +0.12
    0.5%
    29
    +0.11
    0.5%
    268
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.07
    314
    +0.11
    -0.01
    659
    +0.10
    0.06
    Negative Logits
    anol
    -0.65
    anova
    -0.62
    ANS
    -0.62
    inals
    -0.62
    itors
    -0.60
    eper
    -0.60
    atown
    -0.59
    iencies
    -0.58
    ents
    -0.58
    bia
    -0.58
    POSITIVE LOGITS
    DragonMagazine
    0.70
    rase
    0.68
    é¾įå¥ij士
    0.66
    mg
    0.64
    cour
    0.64
    roid
    0.62
    ook
    0.62
    hal
    0.61
    razil
    0.61
    hya
    0.60
    Activations Density 0.794%

    No Known Activations