© 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. MLP Post
    9. 0-MLP-SM
    11. 31054
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "event."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    219
    +0.13
    0.8%
    376
    +0.11
    0.7%
    100
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    219
    +0.13
    0.02
    471
    +0.11
    0.02
    320
    +0.11
    0.02
    Negative Logits
    ·
    -1.94
    IJ
    -1.72
    ¸
    -1.69
    ¿
    -1.60
    ³
    -1.57
     ?>
    -1.54
     answer
    -1.52
     \%
    -1.51
     adulthood
    -1.51
    "?"
    -1.50
    POSITIVE LOGITS
    ually
    2.33
    uality
    2.07
    nel
    1.88
    nell
    1.88
    iga
    1.87
    hole
    1.84
    finder
    1.83
    grounds
    1.70
    sworth
    1.65
    maker
    1.63
    Activations Density 0.016%

    No Known Activations