© 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. 2-RES-SM
    11. 12356
    Prev
    Next
    INDEX
    Explanations

    references to Docker and its commands in a containerization context

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    156
    +0.24
    1.4%
    321
    +0.14
    0.8%
    410
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.24
    0.01
    410
    +0.14
    0.02
    80
    +0.14
    0.02
    Negative Logits
     unanimous
    -1.65
     misunderstanding
    -1.46
     persu
    -1.44
     nausea
    -1.43
     unintended
    -1.42
     deaf
    -1.41
    rely
    -1.41
     intention
    -1.39
     omission
    -1.39
    atre
    -1.39
    POSITIVE LOGITS
    flare
    1.98
    beans
    1.89
    ://
    1.88
     networks
    1.71
    hub
    1.67
     logs
    1.64
    gov
    1.64
    Hub
    1.64
    ¢
    1.57
    docker
    1.54
    Activations Density 0.158%

    No Known Activations