© 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. 11779
    Prev
    Next
    INDEX
    Explanations

    phrases or elements related to programming, technical specifications, and numerical data

    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
    182
    +0.14
    0.8%
    24
    +0.12
    0.7%
    458
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    182
    +0.14
    0.10
    20
    +0.12
    0.09
    453
    +0.12
    0.04
    Negative Logits
    owitz
    -1.53
    idades
    -1.53
    arters
    -1.42
    inth
    -1.41
    ites
    -1.36
    rue
    -1.34
    ités
    -1.29
    ativa
    -1.29
    gens
    -1.28
    inates
    -1.28
    POSITIVE LOGITS
     M
    4.31
    M
    3.69
     m
    3.19
     MM
    3.07
    MM
    3.01
     MT
    2.98
    MT
    2.98
     MB
    2.89
    MN
    2.87
    MP
    2.83
    Activations Density 2.244%

    No Known Activations