© 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. 32480
    Prev
    Next
    INDEX
    Explanations

    articles and determiner phrases

    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
    369
    +0.19
    1.1%
    436
    +0.14
    0.8%
    321
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    436
    +0.19
    0.07
    149
    +0.14
    0.05
    458
    +0.12
    0.05
    Negative Logits
    Ļª
    -2.40
    arias
    -1.75
    Ĭ
    -1.73
    ¾
    -1.70
    ±
    -1.68
     cards
    -1.68
    Īĺ
    -1.63
     CDs
    -1.63
    Ĺ
    -1.60
    ystems
    -1.60
    POSITIVE LOGITS
    uster
    1.86
     comparison
    1.67
     particularly
    1.63
     further
    1.60
     measure
    1.58
     consequence
    1.57
    STM
    1.54
    gree
    1.54
    then
    1.53
    ston
    1.52
    Activations Density 0.416%

    No Known Activations