© 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. 1-RES-SM
    11. 25932
    Prev
    Next
    INDEX
    Explanations

    words related to electricity and electrical systems

    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
    156
    +0.23
    1.3%
    219
    +0.11
    0.7%
    508
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    508
    +0.23
    0.01
    429
    +0.11
    0.01
    219
    +0.11
    0.01
    Negative Logits
     mismo
    -1.65
     particular
    -1.59
     final
    -1.54
     criticize
    -1.53
     intend
    -1.51
    Å¡ÃŃ
    -1.50
    ções
    -1.48
     dramatic
    -1.48
     euthan
    -1.46
    inois
    -1.44
    POSITIVE LOGITS
    £
    1.90
    ¡
    1.78
    iens
    1.77
    ISING
    1.75
    ulence
    1.73
    ¬
    1.72
    lectric
    1.67
    rically
    1.66
    ¢
    1.64
    ĸ
    1.58
    Activations Density 0.042%

    No Known Activations