© 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. 28304
    Prev
    Next
    INDEX
    Explanations

    keywords or symbols related to numerical values or measurements

    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
    142
    +0.12
    0.7%
    414
    +0.11
    0.6%
    292
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    437
    +0.12
    0.01
    292
    +0.11
    0.01
    142
    +0.10
    0.01
    Negative Logits
     regulation
    -1.52
    om
    -1.47
     agg
    -1.45
     ORDER
    -1.43
    omer
    -1.41
     Order
    -1.39
     controversy
    -1.38
    ophil
    -1.34
     Enron
    -1.34
     Oil
    -1.34
    POSITIVE LOGITS
    ¼
    2.85
    Ĵ
    2.42
    IJ
    1.94
    ¸
    1.88
    «
    1.87
    į
    1.80
    ¡
    1.77
    ĻĤ
    1.76
    jours
    1.70
    ¯
    1.70
    Activations Density 0.031%

    No Known Activations