© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 12060
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to anatomy and specific body parts

    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
    448
    +0.12
    0.7%
    377
    +0.12
    0.6%
    405
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    18
    +0.12
    0.01
    30
    +0.12
    0.00
    391
    +0.11
    0.01
    Negative Logits
    ĥ½
    -2.07
    mate
    -2.03
    fully
    -1.84
    chitz
    -1.80
    xico
    -1.75
    ĥ
    -1.64
    hift
    -1.63
    mith
    -1.59
    aliana
    -1.59
    iamo
    -1.56
    POSITIVE LOGITS
     neuropathy
    2.39
     blood
    2.34
     nerve
    2.27
     venous
    2.01
    cy
    1.97
     nerves
    1.96
    blood
    1.93
     organs
    1.92
     tissues
    1.85
     veins
    1.79
    Activations Density 0.019%

    No Known Activations