© 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. 31178
    Prev
    Next
    INDEX
    Explanations

    references to family

    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
    362
    +0.15
    0.9%
    87
    +0.12
    0.7%
    507
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.15
    0.04
    507
    +0.12
    0.04
    102
    +0.12
    0.04
    Negative Logits
    ĥ½
    -2.56
    Ļª
    -2.48
    ĨĴ
    -2.47
    -2.46
    -2.46
     ↵
    -2.46
    č↵č↵
    -2.46
    -2.46
    ↵
    -2.46
    č↵
    -2.46
    POSITIVE LOGITS
    table
    1.78
     quarters
    1.78
    erals
    1.70
     resem
    1.65
    doms
    1.65
    dom
    1.62
    liness
    1.56
     affairs
    1.53
     matters
    1.50
    room
    1.49
    Activations Density 0.038%

    No Known Activations