© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8732
    Prev
    Next
    INDEX
    Explanations

    terms related to immune function and health conditions affecting the immune system

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    348
    +0.18
    1.0%
    78
    +0.13
    0.7%
    125
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.18
    0.01
    275
    +0.13
    0.01
    113
    +0.12
    0.01
    Negative Logits
    als
    -1.76
    ateur
    -1.71
    aré
    -1.71
    fully
    -1.70
    orems
    -1.66
    owing
    -1.66
    hots
    -1.66
    hire
    -1.66
    lights
    -1.63
    ateurs
    -1.62
    POSITIVE LOGITS
     responses
    1.90
     infiltr
    1.89
     response
    1.85
     reactivity
    1.78
     cells
    1.69
     defenses
    1.68
    mitted
    1.60
     microenvironment
    1.58
     disorders
    1.55
     checkpoint
    1.55
    Activations Density 0.029%

    No Known Activations