© 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. 25329
    Prev
    Next
    INDEX
    Explanations

    references to couples and marriages, particularly focusing on their circumstances and dynamics

    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
    376
    +0.19
    1.1%
    87
    +0.15
    0.9%
    257
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.19
    0.01
    229
    +0.15
    0.01
    257
    +0.11
    0.01
    Negative Logits
    ´
    -3.72
    -3.71
     ↵
    -3.71
    č↵
    -3.71
    -3.71
    -3.71
    ↵  ↵
    -3.71
    ↵
    -3.71
    ↵
    -3.71
    ↵↵
    -3.71
    POSITIVE LOGITS
    cript
    2.26
    creen
    1.95
    quet
    1.75
    able
    1.73
    eto
    1.69
    ystems
    1.68
    ystem
    1.65
    tee
    1.65
     fixture
    1.62
    heet
    1.61
    Activations Density 0.011%

    No Known Activations