© 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. 2-MLP-SM
    11. 22356
    Prev
    Next
    INDEX
    Explanations

    instances of mathematical operations and variables

    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/2-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.2.hook_mlp_out
    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
    262
    +0.13
    0.7%
    470
    +0.12
    0.7%
    370
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    62
    +0.13
    0.02
    97
    +0.12
    0.01
    262
    +0.12
    0.01
    Negative Logits
    phis
    -1.78
    iah
    -1.52
    owski
    -1.52
    ableness
    -1.48
    born
    -1.46
    roid
    -1.42
     LLP
    -1.42
     wards
    -1.41
    schild
    -1.39
    arily
    -1.38
    POSITIVE LOGITS
    documentclass
    2.21
    ĻĤ
    1.46
     Oslo
    1.42
    ŀ
    1.41
    you
    1.40
     %>
    1.40
    hr
    1.40
    uez
    1.40
     mention
    1.38
    $.[]{
    1.36
    Activations Density 0.168%

    No Known Activations