© 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. 2-MLP-SM
    11. 22346
    Prev
    Next
    INDEX
    Explanations

    content related to software licenses, specifically free software licenses

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    510
    +0.12
    0.7%
    414
    +0.12
    0.7%
    259
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.12
    0.02
    414
    +0.12
    0.01
    103
    +0.11
    0.03
    Negative Logits
     reductase
    -1.45
     disclaim
    -1.38
    virtual
    -1.36
     Esther
    -1.35
     Perl
    -1.32
     readable
    -1.28
     continued
    -1.27
    uously
    -1.26
    devel
    -1.25
     Atty
    -1.25
    POSITIVE LOGITS
    ļ
    2.08
    »
    1.86
    ¼
    1.78
    ¯
    1.77
    .:
    1.71
    ª
    1.70
    ī
    1.69
    ł
    1.67
    ¡
    1.66
    veis
    1.66
    Activations Density 0.187%

    No Known Activations