© 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 EvalsExportsinterp-engineNEWAPI 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. 13950
    Prev
    Next
    INDEX
    Explanations

    terms related to antioxidants and their biochemical properties

    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
    216
    +0.14
    0.8%
    85
    +0.12
    0.7%
    56
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.14
    0.04
    216
    +0.12
    0.05
    356
    +0.11
    0.04
    Negative Logits
     Afghan
    -1.83
     Afghanistan
    -1.83
     lingu
    -1.78
     missionary
    -1.75
     encoder
    -1.73
     Nebraska
    -1.69
    érie
    -1.66
     Caption
    -1.61
     Skype
    -1.60
     Trek
    -1.57
    POSITIVE LOGITS
     antioxidant
    3.86
     antioxidants
    3.80
     superoxide
    3.62
     oxidative
    3.59
     redox
    3.46
     antioxid
    3.29
     perox
    3.19
     oxid
    3.17
     ROS
    3.11
    oxid
    3.04
    Activations Density 0.349%

    No Known Activations