© 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. 26324
    Prev
    Next
    INDEX
    Explanations

    keywords related to community activities and lifestyles, particularly those involving leisure, advocacy, and social events

    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
    56
    +0.14
    0.9%
    362
    +0.11
    0.7%
    263
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.14
    0.05
    56
    +0.11
    -0.02
    66
    +0.11
    0.08
    Negative Logits
    ĸ´
    -3.96
    Īĺ
    -3.96
    ī
    -3.96
    Ļª
    -3.81
    »
    -3.79
    ij
    -3.75
    į
    -3.74
    Į
    -3.73
    ı
    -3.71
    ļ
    -3.71
    POSITIVE LOGITS
    mas
    1.99
    bies
    1.84
    worker
    1.82
     tours
    1.76
    employee
    1.73
     proceeds
    1.73
     trips
    1.71
     fees
    1.69
     industry
    1.69
    hops
    1.64
    Activations Density 1.587%

    No Known Activations