© 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. 30931
    Prev
    Next
    INDEX
    Explanations

    instances of the word "notice."

    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
    376
    +0.19
    1.1%
    148
    +0.14
    0.8%
    314
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    235
    +0.19
    0.03
    314
    +0.14
    0.02
    394
    +0.11
    0.02
    Negative Logits
    ´
    -2.50
    ĥ½
    -2.40
    Ľ
    -2.15
    Ŀ
    -2.11
    -1.95
    ↵
    -1.95
    ↵  ³³³
    -1.95
     ↵
    -1.95
    ↵
    -1.95
    ↵
    -1.95
    POSITIVE LOGITS
    ably
    2.28
     notes
    1.51
     inf
    1.46
     utter
    1.44
     warnings
    1.41
    istical
    1.40
    idious
    1.40
     gaps
    1.39
    holder
    1.37
    ugu
    1.37
    Activations Density 0.017%

    No Known Activations