© 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. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 29924
    Prev
    Next
    INDEX
    Explanations

    instances of the word "just"

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    486
    +0.15
    0.9%
    354
    +0.14
    0.8%
    110
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    486
    +0.15
    0.05
    110
    +0.14
    0.04
    354
    +0.12
    0.04
    Negative Logits
    phrine
    -1.90
    ¾
    -1.78
    ij
    -1.78
    Ĥ¬
    -1.75
    ļ
    -1.71
    stdlib
    -1.69
    Ŀ
    -1.66
    ı
    -1.62
    Ģ
    -1.54
    Ľ
    -1.53
    POSITIVE LOGITS
    say
    1.98
    ifi
    1.96
    IFY
    1.95
    icia
    1.80
    Answer
    1.72
    ifying
    1.62
    ified
    1.61
    isance
    1.59
    ifiable
    1.58
    ify
    1.58
    Activations Density 0.176%

    No Known Activations