© 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. 12460
    Prev
    Next
    INDEX
    Explanations

    topics related to infections and bacterial conditions

    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
    +0.21
    1.2%
    184
    +0.12
    0.7%
    509
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.21
    0.02
    391
    +0.12
    0.04
    18
    +0.11
    0.04
    Negative Logits
     animation
    -1.64
    forth
    -1.53
     Animation
    -1.46
    ôt
    -1.46
     yours
    -1.44
     overhaul
    -1.43
     chairs
    -1.43
     expectations
    -1.43
    coming
    -1.41
    apshot
    -1.41
    POSITIVE LOGITS
     infections
    2.57
     pathogens
    2.52
     pneumoniae
    2.37
     strains
    2.33
     pathogen
    2.27
     microorganisms
    2.23
     infect
    2.23
     infection
    2.20
     bacteria
    2.19
     bacterium
    2.15
    Activations Density 0.156%

    No Known Activations