© 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 EvalsExportsAPI 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. 28495
    Prev
    Next
    INDEX
    Explanations

    references to Malaysia or its people

    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
    369
    +0.16
    0.9%
    71
    +0.14
    0.8%
    377
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.16
    0.02
    494
    +0.14
    0.02
    80
    +0.12
    0.02
    Negative Logits
    hern
    -1.74
      ↵
    -1.66
    cluding
    -1.56
     uterus
    -1.50
    quired
    -1.47
    rocy
    -1.45
     scheduled
    -1.45
     complete
    -1.45
    ub
    -1.43
     bowel
    -1.42
    POSITIVE LOGITS
     recognizes
    2.02
     Airlines
    1.76
    naire
    1.72
    manship
    1.71
    film
    1.70
     herself
    1.67
     understands
    1.66
     themselves
    1.59
    izumab
    1.55
     improves
    1.54
    Activations Density 3.708%

    No Known Activations