© 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. 25250
    Prev
    Next
    INDEX
    Explanations

    references to medicine and medical terminology

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.25
    1.5%
    173
    +0.16
    1.0%
    376
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    173
    +0.25
    0.01
    184
    +0.16
    0.01
    356
    +0.14
    0.01
    Negative Logits
    ¯
    -1.77
    ĥ
    -1.72
    apine
    -1.69
    ĥ½
    -1.65
     consent
    -1.64
    ı
    -1.55
    §
    -1.53
     yours
    -1.51
    ¬
    -1.50
     adulthood
    -1.50
    POSITIVE LOGITS
    ouin
    1.57
    ieux
    1.57
    arum
    1.56
    istry
    1.52
    erate
    1.52
    imeter
    1.51
    roads
    1.49
    acre
    1.49
    IER
    1.49
    brane
    1.48
    Activations Density 0.011%

    No Known Activations