© 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. 25093
    Prev
    Next
    INDEX
    Explanations

    references to the name Kennedy in various contexts

    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
    71
    +0.15
    0.9%
    410
    +0.14
    0.9%
    156
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.15
    0.02
    345
    +0.14
    0.02
    511
    +0.13
    0.01
    Negative Logits
    ĥ½
    -1.83
    efore
    -1.56
    iler
    -1.52
     previous
    -1.50
    igm
    -1.50
     Later
    -1.46
    iled
    -1.44
     entirety
    -1.43
    orters
    -1.41
     Jama
    -1.40
    POSITIVE LOGITS
    abad
    1.82
    yard
    1.77
    opan
    1.72
    manship
    1.70
    shire
    1.70
    istan
    1.69
    ullah
    1.66
    hammer
    1.64
    fors
    1.62
    hole
    1.62
    Activations Density 0.271%

    No Known Activations