© 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. 30990
    Prev
    Next
    INDEX
    Explanations

    references to mothers and fathers in the context of family and parental roles

    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
    156
    +0.32
    1.9%
    87
    +0.14
    0.8%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.32
    0.01
    499
    +0.14
    0.01
    265
    +0.12
    0.01
    Negative Logits
    woke
    -1.67
    rap
    -1.54
    rians
    -1.54
    riel
    -1.50
     BGCOLOR
    -1.48
    reo
    -1.47
    ¯
    -1.42
    ria
    -1.41
    ONS
    -1.37
    ffen
    -1.35
    POSITIVE LOGITS
    ière
    1.62
    hole
    1.59
    manship
    1.56
    erals
    1.56
    ground
    1.54
    enda
    1.51
    stown
    1.45
    hoe
    1.45
    het
    1.45
    oft
    1.45
    Activations Density 0.017%

    No Known Activations