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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 25826
    Prev
    Next
    INDEX
    Explanations

    statements related to listing or asking about factors of numbers

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    178
    +0.16
    0.9%
    387
    +0.15
    0.8%
    294
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    424
    +0.16
    0.02
    210
    +0.15
    0.01
    410
    +0.13
    0.01
    Negative Logits
    ois
    -1.57
    mate
    -1.56
     believing
    -1.54
    ainer
    -1.50
    ech
    -1.50
    aten
    -1.50
    ivism
    -1.49
     whom
    -1.47
     predicting
    -1.47
     evaluating
    -1.46
    POSITIVE LOGITS
     influx
    1.55
     LIMITED
    1.55
      ↵
    1.53
    iginally
    1.43
     LOT
    1.42
     auction
    1.42
     embargo
    1.40
    etc
    1.38
     arrangement
    1.32
     Lot
    1.31
    Activations Density 0.105%

    No Known Activations