© 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. 30897
    Prev
    Next
    INDEX
    Explanations

    references to the name "Mitt Romney."

    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
    59
    +0.17
    0.9%
    111
    +0.13
    0.7%
    347
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    230
    +0.17
    0.01
    55
    +0.13
    0.01
    59
    +0.11
    0.01
    Negative Logits
    cing
    -1.59
     perin
    -1.52
     import
    -1.50
     Miss
    -1.49
     her
    -1.48
     Later
    -1.48
     maternal
    -1.46
    iginally
    -1.44
     virgin
    -1.43
     western
    -1.43
    POSITIVE LOGITS
    baum
    2.01
    arro
    1.89
    stock
    1.88
    feld
    1.88
    genstein
    1.85
    chitz
    1.80
    wo
    1.71
    iewicz
    1.69
    gens
    1.68
    endor
    1.67
    Activations Density 0.447%

    No Known Activations