© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 31023
    Prev
    Next
    INDEX
    Explanations

    references to the word "nerve"

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    376
    +0.13
    0.8%
    31
    +0.10
    0.6%
    308
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    31
    +0.13
    0.01
    331
    +0.10
    0.01
    259
    +0.10
    0.01
    Negative Logits
     Naz
    -1.67
    olor
    -1.62
     Later
    -1.47
    ı
    -1.46
     Que
    -1.43
     -->
    -1.42
    Č
    -1.39
    .</
    -1.39
    woke
    -1.37
     Then
    -1.32
    POSITIVE LOGITS
    fault
    1.56
    igent
    1.55
    ibus
    1.47
    beam
    1.47
    gru
    1.46
    craft
    1.44
    ovo
    1.43
    stock
    1.42
    hart
    1.40
    notes
    1.37
    Activations Density 0.136%

    No Known Activations