© 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. 12092
    Prev
    Next
    INDEX
    Explanations

    terms related to oxidative stress and its effects on health

    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
    2
    +0.15
    0.8%
    415
    +0.14
    0.8%
    11
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    11
    +0.15
    0.01
    2
    +0.14
    0.01
    195
    +0.13
    0.01
    Negative Logits
    usement
    -1.90
    sembl
    -1.88
    oscope
    -1.81
    orect
    -1.69
    ureus
    -1.68
    owned
    -1.68
    ounger
    -1.68
    ontally
    -1.67
    ician
    -1.61
    cheon
    -1.57
    POSITIVE LOGITS
     phosphorylation
    2.14
     stress
    1.94
     degradation
    1.93
     metabolism
    1.90
     glycol
    1.89
     pathways
    1.87
     mechanisms
    1.83
     pressures
    1.81
     stresses
    1.70
     damage
    1.68
    Activations Density 0.043%

    No Known Activations