© 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. 29991
    Prev
    Next
    INDEX
    Explanations

    references to the name "Michael."

    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
    156
    +0.28
    1.6%
    369
    +0.22
    1.3%
    376
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    450
    +0.28
    0.03
    341
    +0.22
    0.03
    369
    +0.11
    0.03
    Negative Logits
    "?"
    -1.98
    ¿½
    -1.83
    ounder
    -1.68
     previous
    -1.58
    TRODUCTION
    -1.52
     late
    -1.46
     female
    -1.46
    ĥ½
    -1.44
     ago
    -1.42
    lor
    -1.41
    POSITIVE LOGITS
    opan
    1.69
    aho
    1.65
    ceral
    1.63
    ા
    1.56
    stown
    1.53
    holes
    1.48
    hole
    1.44
    quito
    1.44
    icillin
    1.43
     ratios
    1.42
    Activations Density 0.013%

    No Known Activations