© 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. 30240
    Prev
    Next
    INDEX
    Explanations

    references to pulmonary conditions or terms

    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
    +0.33
    1.9%
    377
    +0.17
    1.0%
    148
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    377
    +0.33
    0.01
    319
    +0.17
    0.01
    267
    +0.12
    0.01
    Negative Logits
    rapeut
    -1.56
    dule
    -1.52
    eting
    -1.42
    oci
    -1.40
    derer
    -1.39
    zos
    -1.39
    rocy
    -1.33
    agles
    -1.32
     Selected
    -1.31
    zek
    -1.29
    POSITIVE LOGITS
    ĻĤ
    1.68
    oon
    1.48
    wise
    1.37
    Congress
    1.34
     aside
    1.34
    istor
    1.33
    imeter
    1.30
    waves
    1.29
    FW
    1.28
     aisle
    1.26
    Activations Density 0.005%

    No Known Activations