© 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. 22373
    Prev
    Next
    INDEX
    Explanations

    references to numerical or statistical data

    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
    156
    +0.15
    0.9%
    476
    +0.14
    0.8%
    316
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    385
    +0.15
    0.07
    300
    +0.14
    0.01
    432
    +0.10
    0.03
    Negative Logits
    ĻĤ
    -2.55
    Īĺ
    -1.76
    »¿
    -1.75
    ĸ´
    -1.71
    ))$.
    -1.70
    reate
    -1.68
    Ī
    -1.62
    Į
    -1.49
    £
    -1.49
    approximately
    -1.46
    POSITIVE LOGITS
    iers
    1.70
     substitute
    1.49
     commentator
    1.47
     blogger
    1.45
    iator
    1.43
     rou
    1.43
    iac
    1.40
     pylori
    1.39
    leader
    1.39
    seys
    1.37
    Activations Density 1.647%

    No Known Activations