© 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. 28396
    Prev
    Next
    INDEX
    Explanations

    references to vitamins and minerals, particularly their significance in nutrition

    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
    81
    +0.13
    0.7%
    156
    +0.13
    0.7%
    301
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.13
    0.04
    365
    +0.13
    0.03
    329
    +0.11
    0.04
    Negative Logits
    's
    -2.31
     charts
    -1.90
    bing
    -1.85
     agreements
    -1.71
    charts
    -1.68
    asone
    -1.67
     drafts
    -1.64
     agrees
    -1.62
    grams
    -1.58
    esy
    -1.55
    POSITIVE LOGITS
    ystems
    2.19
    ystem
    2.02
    mith
    1.97
    pace
    1.97
    pire
    1.93
    hift
    1.88
    erver
    1.87
    ucker
    1.83
    creen
    1.83
    linger
    1.74
    Activations Density 0.128%

    No Known Activations