© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 29880
    Prev
    Next
    INDEX
    Explanations

    references to medical imaging techniques

    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
    +0.24
    1.4%
    443
    +0.14
    0.8%
    451
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    451
    +0.24
    0.01
    443
    +0.14
    0.01
    320
    +0.13
    0.01
    Negative Logits
    unnumbered
    -1.67
    arding
    -1.53
    ansen
    -1.50
     suicidal
    -1.40
    woke
    -1.37
    ikov
    -1.37
     bargaining
    -1.34
    uku
    -1.32
    chard
    -1.32
     breastfeeding
    -1.31
    POSITIVE LOGITS
    ior
    1.63
     device
    1.57
     holes
    1.54
    stock
    1.49
     area
    1.49
     theaters
    1.47
     outfit
    1.46
    bird
    1.44
    hole
    1.43
     indications
    1.42
    Activations Density 0.066%

    No Known Activations