© 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. 28282
    Prev
    Next
    INDEX
    Explanations

    references to monuments

    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
    299
    +0.13
    0.8%
    352
    +0.12
    0.7%
    160
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    80
    +0.13
    0.01
    299
    +0.12
    0.01
    134
    +0.12
    0.01
    Negative Logits
    '));
    -1.68
     Distributed
    -1.66
    attering
    -1.61
    obbsee
    -1.60
     EIGEN
    -1.51
    "));
    -1.49
     _________
    -1.46
     ."
    -1.46
    "?"
    -1.45
    '))
    -1.44
    POSITIVE LOGITS
    ary
    1.97
    aries
    1.90
    ului
    1.90
    al
    1.84
    ÅĽci
    1.83
    ière
    1.77
    arian
    1.75
    iewicz
    1.74
    agem
    1.74
    holder
    1.71
    Activations Density 0.013%

    No Known Activations