© 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. 28279
    Prev
    Next
    INDEX
    Explanations

    references to Apple Mac products

    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
    410
    +0.17
    1.0%
    369
    +0.17
    1.0%
    471
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    440
    +0.17
    0.02
    471
    +0.17
    0.02
    447
    +0.12
    0.02
    Negative Logits
    ¼
    -4.34
    Ļª
    -4.12
    ĨĴ
    -4.05
    ĥ½
    -3.91
    ĸ´
    -3.90
    ķ
    -3.88
    ij
    -3.86
    ¯
    -3.84
    ¿½
    -3.76
    Ħ
    -3.73
    POSITIVE LOGITS
    aul
    2.04
    iej
    2.01
    culated
    1.82
    beth
    1.79
    chitz
    1.71
    TeX
    1.69
    Gy
    1.64
    arthy
    1.62
    Book
    1.61
     equivalents
    1.60
    Activations Density 0.043%

    No Known Activations