© 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. 29894
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to gastrointestinal conditions

    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
    +0.19
    1.1%
    111
    +0.13
    0.7%
    148
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.19
    0.01
    429
    +0.13
    0.01
    71
    +0.13
    0.01
    Negative Logits
    ounces
    -1.68
     stratified
    -1.67
     scheduled
    -1.59
    aked
    -1.55
    rie
    -1.54
    eding
    -1.50
    zzo
    -1.50
    eting
    -1.50
    iling
    -1.46
     happening
    -1.45
    POSITIVE LOGITS
    ĻĤ
    2.82
    Ł
    2.27
    ¡
    2.16
    £
    1.98
    »¿
    1.95
    Ĩ
    1.92
    ®
    1.89
    ŀ
    1.89
    Īĺ
    1.84
    µ
    1.84
    Activations Density 0.007%

    No Known Activations