© 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. 31000
    Prev
    Next
    INDEX
    Explanations

    references to biological substances or conditions related to physical health

    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
    +0.23
    1.3%
    71
    +0.13
    0.8%
    143
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.23
    0.00
    338
    +0.13
    0.00
    111
    +0.12
    0.00
    Negative Logits
     latitude
    -1.51
    uffling
    -1.43
     happier
    -1.39
     distance
    -1.37
    unreadable
    -1.37
    ÑĤÑĮ
    -1.37
    tif
    -1.37
    '>
    -1.35
    hin
    -1.31
     '</
    -1.27
    POSITIVE LOGITS
    ĻĤ
    1.82
    bank
    1.68
    ģ
    1.57
    ĩ
    1.56
    iston
    1.54
    ¡
    1.53
    worker
    1.48
    ĸ
    1.47
     commune
    1.46
    stock
    1.45
    Activations Density 0.235%

    No Known Activations