© 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. 23793
    Prev
    Next
    INDEX
    Explanations

    references to color terminology and palettes

    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
    +0.14
    0.8%
    113
    +0.14
    0.8%
    100
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    113
    +0.14
    0.03
    116
    +0.14
    0.03
    100
    +0.12
    0.03
    Negative Logits
    ±
    -2.13
    Ĥ¬
    -2.09
    ĻĤ
    -2.03
    ĸ´
    -2.02
    Īĺ
    -1.98
    ĭ
    -1.92
    ı
    -1.78
    ľĵ
    -1.77
    ↵
    -1.69
    -1.69
    POSITIVE LOGITS
    imetric
    2.00
    ball
    1.83
    picker
    1.77
    less
    1.75
    blind
    1.75
    imetry
    1.68
     based
    1.62
    imeter
    1.57
    print
    1.54
     badge
    1.52
    Activations Density 0.086%

    No Known Activations