© 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. 1-RES-SM
    11. 29210
    Prev
    Next
    INDEX
    Explanations

    terms related to eye care and ophthalmology

    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
    111
    +0.15
    0.9%
    321
    +0.14
    0.8%
    314
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.03
    314
    +0.14
    0.02
    74
    +0.13
    0.02
    Negative Logits
    Īĺ
    -2.06
    ĨĴ
    -2.06
    Ļª
    -1.90
    Ĥ¬
    -1.77
    ij
    -1.74
    Ħ
    -1.66
    raining
    -1.61
    Ĺ
    -1.56
    upon
    -1.54
    hes
    -1.53
    POSITIVE LOGITS
    agne
    2.00
    \]](
    1.75
    azine
    1.74
    cone
    1.73
    ettes
    1.73
    \][
    1.72
    neys
    1.71
    bian
    1.69
    ang
    1.69
    son
    1.68
    Activations Density 0.096%

    No Known Activations