© 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. Residuals
    9. 4-RES-SM
    11. 11086
    Prev
    Next
    INDEX
    Explanations

    connections between chemical compounds and their effects on health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/4-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    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
    21
    +0.14
    0.8%
    136
    +0.14
    0.8%
    78
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    275
    +0.14
    0.02
    333
    +0.14
    0.03
    199
    +0.13
    0.04
    Negative Logits
     aisle
    -1.66
     budgets
    -1.64
     brackets
    -1.61
     horizon
    -1.59
    ockets
    -1.54
     teachers
    -1.50
     bins
    -1.49
     statistics
    -1.49
    aurus
    -1.49
     textbooks
    -1.46
    POSITIVE LOGITS
     cytotoxicity
    2.69
     antitumor
    2.54
     anticancer
    2.45
     toxicity
    2.39
     pharmacological
    2.34
     Inhibition
    2.31
     antibacterial
    2.25
     cytotoxic
    2.22
     inhibitory
    2.20
     enzyme
    2.17
    Activations Density 0.272%

    No Known Activations