© 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. 14578
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical procedures and conditions, specifically in the context of cell analysis and cytometry

    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
    307
    +0.28
    1.6%
    306
    +0.15
    0.9%
    217
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.28
    0.17
    306
    +0.15
    0.06
    466
    +0.13
    0.13
    Negative Logits
     teachers
    -2.48
     educators
    -2.11
     Teachers
    -2.05
     schools
    -2.02
     teacher
    -2.01
     parents
    -2.01
     Teacher
    -1.97
     school
    -1.93
     Superintendent
    -1.91
     Elementary
    -1.90
    POSITIVE LOGITS
     neutrophils
    2.32
     phag
    2.25
     neutrophil
    2.23
     peritoneal
    2.00
     macrophages
    1.92
     macrophage
    1.91
    "}](#
    1.80
     leukocyte
    1.62
     monocyte
    1.58
     erythrocytes
    1.57
    Activations Density 2.579%

    No Known Activations