© 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. 26652
    Prev
    Next
    INDEX
    Explanations

    instances of the preposition "on."

    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
    478
    +0.27
    1.6%
    69
    +0.26
    1.6%
    98
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.27
    0.21
    152
    +0.26
    0.17
    47
    +0.14
    0.15
    Negative Logits
     Pradesh
    -1.66
    wise
    -1.65
    illon
    -1.60
    raf
    -1.52
    urally
    -1.51
    ishly
    -1.49
    esh
    -1.49
    oud
    -1.36
    mina
    -1.35
    ascus
    -1.34
    POSITIVE LOGITS
    yx
    2.37
    shore
    2.18
    ¿½
    2.18
     behalf
    2.17
    ĨĴ
    2.09
    ĸ´
    2.09
    Ļª
    2.08
    ¶
    2.01
    Īĺ
    1.96
    comes
    1.96
    Activations Density 7.327%

    No Known Activations