© 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. 1-RES-SM
    11. 29478
    Prev
    Next
    INDEX
    Explanations

    references to influenza and related viruses

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    +0.25
    1.4%
    71
    +0.15
    0.9%
    319
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.25
    0.21
    156
    +0.15
    0.10
    271
    +0.12
    0.10
    Negative Logits
    'd
    -1.90
     priori
    -1.58
     learning
    -1.55
    '>
    -1.51
     luck
    -1.51
    oving
    -1.50
    been
    -1.45
    rfloor
    -1.42
     mutual
    -1.42
    ´
    -1.41
    POSITIVE LOGITS
    mong
    1.61
     season
    1.53
    velope
    1.52
     seasons
    1.50
    vist
    1.49
    avian
    1.48
    -$\
    1.44
     HOLDERS
    1.44
     Photograph
    1.44
     immunodeficiency
    1.42
    Activations Density 0.386%

    No Known Activations