© 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. Residuals
    9. 4-RES-SM
    11. 14457
    Prev
    Next
    INDEX
    Explanations

    references to tropical diseases and their associated impacts

    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
    136
    +0.13
    0.7%
    157
    +0.12
    0.7%
    442
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    221
    +0.13
    0.03
    186
    +0.12
    0.04
    30
    +0.12
    0.00
    Negative Logits
     NBA
    -1.95
     guitar
    -1.79
     Angular
    -1.78
     guitars
    -1.76
     basketball
    -1.74
     Fuller
    -1.70
     Jazz
    -1.67
     Basketball
    -1.67
     Cannon
    -1.66
    uitar
    -1.66
    POSITIVE LOGITS
     parasite
    4.08
     malaria
    3.85
     mosquito
    3.77
     parasites
    3.67
     mosquitoes
    3.65
     falciparum
    3.17
     paras
    3.11
     insect
    3.03
     dengue
    3.00
     infect
    2.93
    Activations Density 0.733%

    No Known Activations