© 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. 27519
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the."

    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
    23
    +0.37
    2.4%
    478
    +0.23
    1.5%
    156
    +0.21
    1.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.37
    0.16
    164
    +0.23
    0.14
    98
    +0.21
    0.02
    Negative Logits
    "}](#
    -2.49
    doms
    -1.81
    aña
    -1.80
    esan
    -1.78
    ivat
    -1.75
    añ
    -1.63
     festivals
    -1.63
    gage
    -1.61
    naire
    -1.58
    etto
    -1.57
    POSITIVE LOGITS
     latter
    2.15
     entire
    2.14
    rapy
    2.08
    oretical
    1.94
     same
    1.91
     most
    1.90
     simplest
    1.89
     oldest
    1.81
    rapeut
    1.78
    rapeutics
    1.77
    Activations Density 1.317%

    No Known Activations