© 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. 31056
    Prev
    Next
    INDEX
    Explanations

    concepts related to assistance and caregiving services

    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
    +0.18
    1.0%
    219
    +0.13
    0.7%
    470
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    231
    +0.18
    0.01
    340
    +0.13
    0.01
    341
    +0.13
    0.01
    Negative Logits
    sey
    -1.85
    gered
    -1.60
     enforced
    -1.54
    ching
    -1.52
     affect
    -1.52
     attracted
    -1.49
    kered
    -1.49
     welcomed
    -1.41
    ween
    -1.39
     competed
    -1.37
    POSITIVE LOGITS
    "}](#
    1.79
    textstyle
    1.61
    ppo
    1.59
    iom
    1.42
     Void
    1.41
    phantom
    1.41
    ullary
    1.39
     CONCLUSION
    1.36
    vphantom
    1.36
    antry
    1.33
    Activations Density 0.055%

    No Known Activations