© 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. 27852
    Prev
    Next
    INDEX
    Explanations

    references to institutions or organized entities

    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
    180
    +0.14
    0.8%
    423
    +0.11
    0.6%
    450
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    180
    +0.14
    0.01
    145
    +0.11
    0.01
    423
    +0.11
    0.01
    Negative Logits
     ..."
    -1.57
    ¬
    -1.53
    {
    -1.52
    .."
    -1.52
    Ĥ
    -1.51
    ¤
    -1.50
    ĵ
    -1.49
    Ĵ
    -1.49
    Ļª
    -1.47
    '">
    -1.45
    POSITIVE LOGITS
    aje
    2.02
    agem
    2.00
    yards
    1.91
    eries
    1.86
    forge
    1.85
    ionale
    1.83
    way
    1.80
    craft
    1.71
    yard
    1.70
    acs
    1.65
    Activations Density 0.004%

    No Known Activations