© 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. 2-RES-SM
    11. 10052
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to properties and effects of substances, particularly in a health or scientific context

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    392
    +0.11
    0.6%
    130
    +0.11
    0.6%
    507
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    287
    +0.11
    0.06
    400
    +0.11
    0.02
    392
    +0.10
    0.04
    Negative Logits
    ŀ
    -1.66
    ¡
    -1.65
    ilda
    -1.60
    son
    -1.55
     vice
    -1.50
    roller
    -1.46
    ¿
    -1.46
    pson
    -1.46
    ¾
    -1.42
     Catholic
    -1.42
    POSITIVE LOGITS
    Expected
    1.72
     preclinical
    1.70
     assay
    1.60
     achieved
    1.54
     assays
    1.52
    alities
    1.51
     tested
    1.51
     demonstrated
    1.48
    Experimental
    1.48
    Spec
    1.46
    Activations Density 0.303%

    No Known Activations