© 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. 25193
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "for."

    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
    139
    +0.14
    0.7%
    431
    +0.12
    0.6%
    51
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    335
    +0.14
    0.03
    224
    +0.12
    0.03
    55
    +0.11
    0.03
    Negative Logits
    avy
    -1.72
    aty
    -1.65
    esy
    -1.62
    yyyy
    -1.60
    ually
    -1.56
    theless
    -1.55
    arthy
    -1.49
    quette
    -1.49
    iday
    -1.48
    brew
    -1.48
    POSITIVE LOGITS
    NOS
    1.68
    rig
    1.67
    ras
    1.61
     minds
    1.58
    áĢ¬
    1.42
    OPLE
    1.36
     courage
    1.36
    áĢ¯
    1.35
    GE
    1.33
     engaged
    1.32
    Activations Density 0.016%

    No Known Activations