© 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. 14890
    Prev
    Next
    INDEX
    Explanations

    keywords related to influenza viruses and vaccines

    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
    319
    +0.11
    0.6%
    481
    +0.11
    0.6%
    186
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    120
    +0.11
    0.06
    186
    +0.11
    0.04
    308
    +0.11
    0.03
    Negative Logits
     paddle
    -2.19
     guitar
    -1.83
     jQuery
    -1.82
     Payne
    -1.71
     Angular
    -1.68
     padd
    -1.68
     navig
    -1.67
     canoe
    -1.65
     canvas
    -1.63
     Fuel
    -1.61
    POSITIVE LOGITS
     virus
    4.67
     Virus
    4.23
     viruses
    4.18
     infect
    4.01
     infected
    3.94
    virus
    3.66
     infection
    3.65
     influenza
    3.60
     viral
    3.60
     antiviral
    3.56
    Activations Density 0.752%

    No Known Activations