© 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. 25262
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    374
    +0.14
    0.8%
    250
    +0.12
    0.7%
    509
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.14
    0.36
    23
    +0.12
    0.31
    494
    +0.12
    0.25
    Negative Logits
    ock
    -1.66
    "}](#
    -1.55
    rypt
    -1.49
     liking
    -1.48
    icing
    -1.47
     prod
    -1.47
    bital
    -1.44
     encrypt
    -1.42
    bered
    -1.37
    dess
    -1.36
    POSITIVE LOGITS
    eles
    1.52
    anuts
    1.51
     within
    1.41
    fits
    1.38
     lawsuits
    1.38
     suffered
    1.38
    wide
    1.36
    reements
    1.36
    aren
    1.36
    within
    1.32
    Activations Density 3.060%

    No Known Activations