© 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. 14886
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to electronics and circuit design

    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
    98
    +0.12
    0.7%
    453
    +0.12
    0.7%
    61
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    98
    +0.12
    0.01
    453
    +0.12
    0.04
    294
    +0.12
    0.04
    Negative Logits
     thirst
    -1.80
    lickr
    -1.78
     euthan
    -1.75
     osm
    -1.67
     hasht
    -1.66
     lions
    -1.64
     yogurt
    -1.63
     tweet
    -1.63
    nesty
    -1.59
     hike
    -1.58
    POSITIVE LOGITS
     solder
    2.95
     electronics
    2.83
     circuits
    2.80
     PCB
    2.78
     circuit
    2.71
     chip
    2.68
     semiconductor
    2.63
     electronic
    2.61
     wiring
    2.61
    chip
    2.57
    Activations Density 0.849%

    No Known Activations