© 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. 30900
    Prev
    Next
    INDEX
    Explanations

    references to the concept of compression

    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
    156
    +0.15
    0.9%
    217
    +0.13
    0.8%
    178
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    178
    +0.15
    0.01
    217
    +0.13
    0.01
    114
    +0.12
    0.01
    Negative Logits
    woke
    -1.80
    unnumbered
    -1.80
    ---|---
    -1.63
     slightest
    -1.63
     happier
    -1.52
     gone
    -1.50
     embark
    -1.49
     vengeance
    -1.48
    lı
    -1.47
     friends
    -1.46
    POSITIVE LOGITS
     factor
    1.82
    ist
    1.74
    apore
    1.62
    iere
    1.60
    idone
    1.60
    iston
    1.58
    ij
    1.58
    tees
    1.54
    quart
    1.54
    ante
    1.53
    Activations Density 0.007%

    No Known Activations