© 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. MLP Post
    9. 0-MLP-SM
    11. 29838
    Prev
    Next
    INDEX
    Explanations

    references to the Linux operating system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    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
    +0.12
    0.7%
    375
    +0.12
    0.7%
    71
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    375
    +0.12
    0.01
    143
    +0.12
    0.01
    419
    +0.12
    0.01
    Negative Logits
     welcome
    -1.57
    icity
    -1.57
    ging
    -1.57
    cluding
    -1.56
     wife
    -1.54
     maternal
    -1.54
    č
    -1.50
     mothers
    -1.50
    fections
    -1.47
     less
    -1.46
    POSITIVE LOGITS
    ª
    2.08
    estock
    2.04
    inux
    1.85
    sted
    1.82
    ARY
    1.75
    çois
    1.71
    quist
    1.71
    vre
    1.69
    umber
    1.69
    krit
    1.68
    Activations Density 0.016%

    No Known Activations