© 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. 11394
    Prev
    Next
    INDEX
    Explanations

    references to medical cases and statistics related to diseases

    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
    62
    +0.11
    0.6%
    498
    +0.11
    0.6%
    65
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.11
    0.03
    62
    +0.11
    0.01
    401
    +0.11
    0.01
    Negative Logits
    watson
    -1.97
     role
    -1.56
    80211
    -1.54
    thon
    -1.52
     answer
    -1.44
     meditation
    -1.43
     Corps
    -1.41
     vez
    -1.38
    rano
    -1.37
    inux
    -1.36
    POSITIVE LOGITS
     involving
    2.31
    icle
    2.17
     diagnosed
    2.09
    °
    2.06
    ij
    1.92
     presenting
    1.91
     of
    1.90
     hospitalized
    1.90
    icular
    1.89
    ĭ
    1.87
    Activations Density 0.127%

    No Known Activations