© 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. 23985
    Prev
    Next
    INDEX
    Explanations

    terms related to technical systems and management processes

    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
    156
    +0.27
    1.5%
    130
    +0.12
    0.7%
    333
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    365
    +0.27
    0.07
    194
    +0.12
    0.08
    156
    +0.12
    0.09
    Negative Logits
     Avenue
    -1.72
    blogger
    -1.71
     edition
    -1.68
    rah
    -1.63
    ène
    -1.61
     Edition
    -1.54
     год
    -1.53
     appeal
    -1.52
     story
    -1.50
    ¬
    -1.49
    POSITIVE LOGITS
    mapsto
    1.67
    ")]
    1.64
    PROC
    1.56
    gluc
    1.50
    Control
    1.50
    nolimits
    1.49
    impl
    1.48
    limits
    1.48
    IME
    1.47
    ield
    1.47
    Activations Density 1.001%

    No Known Activations