© 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. 29807
    Prev
    Next
    INDEX
    Explanations

    phrases indicating eternal concepts or commitments

    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
    376
    +0.14
    0.8%
    165
    +0.12
    0.7%
    251
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    322
    +0.14
    0.02
    251
    +0.12
    0.02
    132
    +0.11
    0.02
    Negative Logits
     whole
    -1.69
    ween
    -1.57
     strongest
    -1.50
    inoc
    -1.49
    apa
    -1.47
     light
    -1.47
    glich
    -1.44
    uge
    -1.42
    hem
    -1.42
    fluoro
    -1.42
    POSITIVE LOGITS
    ł
    1.96
    aires
    1.59
    posts
    1.52
    arily
    1.49
    eting
    1.46
    pieces
    1.41
    Ł
    1.41
    ictions
    1.41
    etry
    1.39
    lessness
    1.38
    Activations Density 0.008%

    No Known Activations