© 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. 1-RES-SM
    11. 27417
    Prev
    Next
    INDEX
    Explanations

    terms related to medical studies evaluating nutritional or therapeutic interventions in patients

    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
    12
    +0.13
    0.7%
    225
    +0.12
    0.7%
    55
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.13
    0.07
    418
    +0.12
    0.01
    478
    +0.11
    -0.01
    Negative Logits
     everywhere
    -1.75
    illion
    -1.58
     plated
    -1.49
     dies
    -1.44
    assic
    -1.43
     palette
    -1.41
    pere
    -1.39
    iser
    -1.37
     creatures
    -1.36
    "}](#
    -1.36
    POSITIVE LOGITS
    teen
    1.71
     participants
    1.60
     evaluated
    1.57
     findings
    1.57
     conclusions
    1.56
     analyzed
    1.54
    \]]{}
    1.49
     statistical
    1.48
     prospectively
    1.46
     Participants
    1.46
    Activations Density 0.983%

    No Known Activations