© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 26413
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings or court-related terminology

    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
    48
    +0.13
    0.7%
    321
    +0.11
    0.6%
    53
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.13
    0.02
    35
    +0.11
    0.02
    322
    +0.11
    0.02
    Negative Logits
    omycin
    -1.71
    \.
    -1.65
    -1.57
    .^[@
    -1.54
     opposed
    -1.54
    ically
    -1.50
    ](
    -1.46
    -1.45
    -1.45
    -1.45
    POSITIVE LOGITS
    Ī
    1.62
    sed
    1.61
    ¿
    1.42
    stanbul
    1.41
    speech
    1.40
    $-
    1.40
     bachelor
    1.40
    vous
    1.39
    iors
    1.38
      ↵
    1.37
    Activations Density 0.162%

    No Known Activations