© 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. 29867
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and treatments

    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
    321
    +0.12
    0.7%
    3
    +0.12
    0.7%
    111
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.12
    0.08
    185
    +0.12
    0.06
    113
    +0.11
    0.06
    Negative Logits
     respectively
    -1.88
    ĥ½
    -1.83
     administering
    -1.49
    ¶
    -1.47
    elp
    -1.47
    ĺ
    -1.43
    KES
    -1.41
    ľ
    -1.40
    »¿
    -1.40
    Īĺ
    -1.39
    POSITIVE LOGITS
    itis
    1.94
    ist
    1.77
    pool
    1.70
    ista
    1.67
    istas
    1.65
    ifacts
    1.63
    ariat
    1.62
    ifications
    1.61
     category
    1.60
    isms
    1.60
    Activations Density 0.481%

    No Known Activations