© 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. 14365
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the"

    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
    98
    +0.17
    1.0%
    478
    +0.15
    0.9%
    23
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    291
    +0.17
    0.08
    35
    +0.15
    0.03
    10
    +0.13
    0.06
    Negative Logits
    idades
    -1.99
    "}](#
    -1.95
    ulation
    -1.85
    ipore
    -1.76
    ounce
    -1.67
    iels
    -1.63
    liness
    -1.60
    ptions
    -1.57
    ulating
    -1.57
    ulations
    -1.55
    POSITIVE LOGITS
    ĨĴ
    3.20
     ↵
    3.03
    3.03
    3.03
    ↵↵
    3.03
    ↵  âĢĥ
    3.03
             ↵
    3.03
    3.03
    3.03
    ↵
    3.03
    Activations Density 0.625%

    No Known Activations