© 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. 22336
    Prev
    Next
    INDEX
    Explanations

    instances of the word "call" and its variations

    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
    271
    +0.15
    0.8%
    91
    +0.12
    0.6%
    416
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    91
    +0.15
    0.04
    219
    +0.12
    0.04
    465
    +0.11
    0.05
    Negative Logits
     confidential
    -1.62
     divisions
    -1.58
     agents
    -1.56
    ±
    -1.55
    ¹
    -1.49
    Ĭ
    -1.48
     conflicts
    -1.46
     theat
    -1.45
    ħ
    -1.43
     artifacts
    -1.43
    POSITIVE LOGITS
    documentclass
    2.41
    ifold
    1.57
    enoid
    1.54
    socket
    1.54
    ifndef
    1.53
    {}{
    1.52
    _,
    1.52
    semble
    1.50
    require
    1.50
    jee
    1.49
    Activations Density 0.477%

    No Known Activations