© 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. 30077
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and concepts

    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
    281
    +0.14
    0.8%
    210
    +0.13
    0.7%
    43
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    210
    +0.14
    0.20
    143
    +0.13
    0.17
    281
    +0.12
    0.20
    Negative Logits
    ħ
    -2.25
    ®
    -2.22
    ľĵ
    -2.07
    ij
    -2.06
    Ĩ
    -2.02
    ļ
    -1.92
    Ģ
    -1.90
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -1.84
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -1.81
    Ļ
    -1.80
    POSITIVE LOGITS
     Teams
    1.54
     Netanyahu
    1.50
     Suite
    1.47
     coats
    1.36
    rounded
    1.34
    ilinear
    1.33
     Horizon
    1.32
     Ãħ
    1.30
    uary
    1.30
    nier
    1.29
    Activations Density 4.750%

    No Known Activations