© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4-RES-SM
    11. 11879
    Prev
    Next
    INDEX
    Explanations

    элементов кода, связанных с пространствами имен и пакетами

    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
    111
    +0.52
    3.9%
    156
    +0.50
    3.8%
    271
    +0.10
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.52
    0.33
    156
    +0.50
    0.23
    71
    +0.10
    0.23
    Negative Logits
    »
    -3.88
    Ł
    -3.83
    ħ
    -3.70
    ®
    -3.67
    ī
    -3.63
    ĭ
    -3.63
    IJ
    -3.63
    ķ
    -3.62
    ·
    -3.61
    ↵↵
    -3.58
    POSITIVE LOGITS
    olia
    1.55
    ella
    1.52
     alone
    1.42
    ://
    1.34
    ael
    1.31
    roup
    1.31
    ensa
    1.29
    uable
    1.29
    ungen
    1.28
     alle
    1.27
    Activations Density 0.311%

    No Known Activations