© 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. 1-RES-SM
    11. 25683
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual or entity named "Moore."

    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
    369
    +0.23
    1.4%
    477
    +0.18
    1.1%
    410
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    477
    +0.23
    0.03
    369
    +0.18
    0.02
    410
    +0.15
    0.03
    Negative Logits
    opic
    -1.70
    otle
    -1.64
    lasses
    -1.59
     authors
    -1.57
    aphyl
    -1.54
    sed
    -1.53
    ocr
    -1.51
    ymmetric
    -1.47
    leftarrow
    -1.46
     favor
    -1.45
    POSITIVE LOGITS
    zes
    2.22
    ira
    2.07
    zier
    1.88
    jiang
    1.83
    ohan
    1.74
    inery
    1.66
    zol
    1.63
    ieties
    1.61
    obs
    1.56
    arts
    1.54
    Activations Density 0.119%

    No Known Activations