© 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. 25972
    Prev
    Next
    INDEX
    Explanations

    terms related to preventive or prophylactic measures in health contexts

    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
    +0.26
    1.5%
    376
    +0.16
    1.0%
    86
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    86
    +0.26
    0.01
    340
    +0.16
    0.01
    78
    +0.12
    0.01
    Negative Logits
    ĨĴ
    -1.59
    ches
    -1.43
    ching
    -1.43
    rocy
    -1.41
    ÑĢÑĥ
    -1.41
    odal
    -1.39
    oard
    -1.38
    bling
    -1.38
    jours
    -1.35
    ibernate
    -1.32
    POSITIVE LOGITS
    "}](#
    2.49
     duties
    1.47
     positions
    1.42
    fix
    1.39
     amounts
    1.38
    ISPR
    1.38
    ently
    1.38
    positions
    1.37
    osine
    1.35
     preparations
    1.31
    Activations Density 0.011%

    No Known Activations