© 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. 4-RES-SM
    11. 8636
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to asset management and programming

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    307
    +0.34
    2.0%
    306
    +0.17
    1.0%
    466
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.34
    0.16
    306
    +0.17
    0.05
    466
    +0.14
    0.12
    Negative Logits
     soybean
    -1.90
     cookies
    -1.89
     hunger
    -1.83
     cooking
    -1.79
     leptin
    -1.77
     craw
    -1.75
     gast
    -1.75
     Guatemala
    -1.74
    agua
    -1.71
     hungry
    -1.70
    POSITIVE LOGITS
    ↵
    4.00
    4.00
    ↵↵
    4.00
    ↵↵
    4.00
    4.00
    4.00
     ↵
    4.00
    ↵
    4.00
    <|outofrange|>
    4.00
    ↵
    4.00
    Activations Density 2.910%

    No Known Activations