© 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. 29242
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Thomas."

    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
    +0.19
    1.1%
    369
    +0.18
    1.0%
    74
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.19
    0.03
    74
    +0.18
    0.02
    499
    +0.13
    0.02
    Negative Logits
    uties
    -2.18
    TRODUCTION
    -1.63
     respondent
    -1.52
    ordinate
    -1.50
    idence
    -1.49
     him
    -1.49
    rap
    -1.48
    ators
    -1.48
     adoption
    -1.47
    "?"
    -1.42
    POSITIVE LOGITS
    quito
    2.27
    chitz
    1.79
    pec
    1.73
    iewicz
    1.64
    stown
    1.59
    icillin
    1.58
    ystem
    1.56
    creen
    1.55
    iang
    1.53
    pere
    1.50
    Activations Density 0.077%

    No Known Activations