© 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. 11471
    Prev
    Next
    INDEX
    Explanations

    terms related to lithium-ion battery components and 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
    21
    +0.22
    1.3%
    397
    +0.16
    0.9%
    270
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.22
    0.09
    21
    +0.16
    0.06
    78
    +0.15
    -0.02
    Negative Logits
    ivent
    -1.61
    ClCompile
    -1.58
    ieren
    -1.49
    amsfonts
    -1.46
    Ñĥж
    -1.42
    arean
    -1.39
    encoding
    -1.38
    obe
    -1.36
    BOOST
    -1.35
     VAT
    -1.34
    POSITIVE LOGITS
     dash
    1.95
     Hawkins
    1.82
     graphite
    1.79
     Wilson
    1.71
     Dash
    1.71
     lithium
    1.69
     Williams
    1.68
     whiskey
    1.68
     Cherokee
    1.67
     Musk
    1.60
    Activations Density 1.926%

    No Known Activations