© 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. 25522
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Si."

    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
    410
    +0.16
    0.9%
    502
    +0.14
    0.8%
    369
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    208
    +0.16
    0.01
    437
    +0.14
    0.01
    502
    +0.14
    0.01
    Negative Logits
    itching
    -1.69
     ?"
    -1.66
    rapeut
    -1.63
      ↵
    -1.61
     entire
    -1.58
    áĢº
    -1.50
    ancell
    -1.46
    cluding
    -1.41
    uscular
    -1.41
     circumference
    -1.40
    POSITIVE LOGITS
    ī
    1.97
    ·¸
    1.93
    ¹
    1.89
    ilee
    1.85
    ĸ
    1.81
    iem
    1.80
    Ī
    1.80
    ļ
    1.74
    oux
    1.73
    obe
    1.72
    Activations Density 0.005%

    No Known Activations