© 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. 24941
    Prev
    Next
    INDEX
    Explanations

    references to specific sections in documents

    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
    414
    +0.16
    1.0%
    389
    +0.14
    0.8%
    220
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    414
    +0.16
    0.02
    220
    +0.14
    0.02
    389
    +0.13
    0.01
    Negative Logits
    terday
    -1.75
     parents
    -1.67
     reflection
    -1.65
     lack
    -1.56
     father
    -1.56
     existence
    -1.55
     ')
    -1.55
    compan
    -1.54
     presence
    -1.52
     sister
    -1.50
    POSITIVE LOGITS
    inux
    2.20
    ist
    2.17
    ais
    2.05
    IVE
    2.04
    naire
    2.01
    ai
    1.86
    ools
    1.83
    ificial
    1.83
    osse
    1.80
    ek
    1.79
    Activations Density 0.012%

    No Known Activations