© 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 EvalsExportsAPI 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. 28385
    Prev
    Next
    INDEX
    Explanations

    specific medical conditions related to cardiac issues

    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
    +0.29
    1.8%
    443
    +0.12
    0.7%
    412
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.29
    0.01
    320
    +0.12
    0.01
    397
    +0.12
    0.00
    Negative Logits
    nered
    -1.71
     else
    -1.54
     spent
    -1.53
     determined
    -1.53
    agles
    -1.50
     href
    -1.48
     happier
    -1.45
     pronounced
    -1.43
     donated
    -1.40
    agle
    -1.39
    POSITIVE LOGITS
    slot
    1.69
    (__
    1.64
    casters
    1.62
    Bank
    1.61
    fork
    1.56
    processor
    1.56
    achine
    1.56
    "}](#
    1.52
    asio
    1.51
    bank
    1.48
    Activations Density 0.009%

    No Known Activations