© 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. MLP Post
    9. 0-MLP-SM
    11. 26877
    Prev
    Next
    INDEX
    Explanations

    references to craftsmanship or crafting-related terms

    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
    389
    +0.14
    0.8%
    496
    +0.12
    0.7%
    465
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    496
    +0.14
    0.02
    389
    +0.12
    0.02
    465
    +0.12
    0.02
    Negative Logits
     href
    -1.62
     anonymous
    -1.61
     existence
    -1.60
     entire
    -1.56
     plaintiff
    -1.56
     behalf
    -1.52
     welcome
    -1.51
    ]>
    -1.51
     anonymity
    -1.50
     latter
    -1.47
    POSITIVE LOGITS
    ī
    2.36
    2.22
    2.22
    ↵        ↵
    2.22
    ↵  ³³³
    2.22
    ↵
    2.22
    2.22
    ↵
    2.22
          ↵
    2.22
    č↵
    2.22
    Activations Density 0.013%

    No Known Activations