© 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. 2-RES-SM
    11. 32468
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence of significant results or observations in research studies

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    185
    +0.14
    0.7%
    298
    +0.11
    0.6%
    418
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    298
    +0.14
    0.05
    185
    +0.11
    0.03
    463
    +0.11
    0.04
    Negative Logits
    onica
    -1.61
     chat
    -1.58
    via
    -1.51
     phone
    -1.50
     inbox
    -1.48
    blogger
    -1.47
    office
    -1.43
     hers
    -1.42
    bows
    -1.41
     quadrup
    -1.41
    POSITIVE LOGITS
    ³
    2.82
    Ń
    2.71
    ²
    2.70
    Ĭ
    2.65
    ¨
    2.58
    ł
    2.54
    ª
    2.46
    Ħ
    2.42
    µ
    2.42
    ¸
    2.40
    Activations Density 0.430%

    No Known Activations