© 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. 23896
    Prev
    Next
    INDEX
    Explanations

    terms related to retinal health and imaging

    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
    71
    +0.18
    1.1%
    156
    +0.15
    0.9%
    404
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.18
    0.01
    404
    +0.15
    0.01
    256
    +0.14
    0.01
    Negative Logits
    ces
    -1.76
     regards
    -1.68
     regard
    -1.67
    iling
    -1.64
    ra
    -1.63
    eding
    -1.60
    mber
    -1.50
     respectful
    -1.49
    reign
    -1.49
    irc
    -1.47
    POSITIVE LOGITS
    ·¸
    2.17
    ¬
    1.87
    ®
    1.75
    ģ
    1.73
    Ń
    1.73
     trademarks
    1.68
    film
    1.66
    ardo
    1.62
    Ģ
    1.57
    ettes
    1.54
    Activations Density 0.049%

    No Known Activations