© 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. 26591
    Prev
    Next
    INDEX
    Explanations

    references to the name "Patrick" in various contexts

    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
    +0.13
    0.7%
    156
    +0.12
    0.7%
    389
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.13
    0.02
    389
    +0.12
    0.02
    59
    +0.12
    0.01
    Negative Logits
     future
    -1.79
    "?"
    -1.78
     previous
    -1.76
    uties
    -1.74
     current
    -1.69
    '?"
    -1.67
     him
    -1.64
    rapeut
    -1.57
     recent
    -1.54
    atur
    -1.51
    POSITIVE LOGITS
    quito
    2.13
    icillin
    1.97
    hth
    1.81
    ulence
    1.72
    iens
    1.69
    het
    1.63
    cloth
    1.62
    alties
    1.60
    zon
    1.60
    issance
    1.59
    Activations Density 0.020%

    No Known Activations