© 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. 14161
    Prev
    Next
    INDEX
    Explanations

    references to specific programming concepts and constructs

    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
    307
    +0.27
    1.6%
    156
    +0.21
    1.2%
    357
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.27
    0.12
    111
    +0.21
    0.11
    274
    +0.14
    0.09
    Negative Logits
    cine
    -1.80
    ató
    -1.77
    smen
    -1.74
    nai
    -1.68
    animals
    -1.67
     films
    -1.62
    edly
    -1.62
    家
    -1.62
    ankind
    -1.61
    film
    -1.56
    POSITIVE LOGITS
    ĨĴ
    3.43
    ı
    3.08
    ľĵ
    3.07
    Ĺ
    2.95
    Ł
    2.94
    Ļª
    2.94
    IJ
    2.85
    į
    2.85
      ↵
    2.82
    ķ
    2.82
    Activations Density 0.789%

    No Known Activations