© 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. 11062
    Prev
    Next
    INDEX
    Explanations

    terms related to inflammation in medical contexts

    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
    68
    +0.12
    0.7%
    371
    +0.12
    0.6%
    47
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.12
    0.01
    68
    +0.12
    0.02
    287
    +0.11
    0.01
    Negative Logits
    finder
    -1.74
    erne
    -1.71
    mozilla
    -1.66
    culator
    -1.62
    erl
    -1.59
     holder
    -1.55
    rar
    -1.55
    arner
    -1.54
     finder
    -1.49
     reliability
    -1.49
    POSITIVE LOGITS
    £
    2.51
     bowel
    2.25
     infiltr
    2.14
     cytokines
    2.11
     diseases
    2.10
     response
    2.04
     pathways
    2.04
     mediators
    2.00
     reactions
    1.99
     cytokine
    1.99
    Activations Density 0.040%

    No Known Activations