© 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. 30144
    Prev
    Next
    INDEX
    Explanations

    specific HTML list item elements

    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
    466
    +0.14
    0.8%
    410
    +0.11
    0.6%
    171
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    466
    +0.14
    0.02
    260
    +0.11
    0.02
    275
    +0.11
    0.02
    Negative Logits
    áĢº
    -2.45
    àµį
    -2.13
    ĵ
    -2.12
    grounds
    -1.74
    »¿
    -1.71
    à±ģ
    -1.65
    ground
    -1.63
    àµ
    -1.62
    áĥĶ
    -1.61
    áŁ
    -1.61
    POSITIVE LOGITS
    aments
    1.73
    emann
    1.70
    enne
    1.67
    aggio
    1.66
    ptin
    1.65
    ende
    1.63
    ée
    1.61
    endor
    1.59
    atÄĥ
    1.50
    zol
    1.48
    Activations Density 0.084%

    No Known Activations