© 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 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. 28638
    Prev
    Next
    INDEX
    Explanations

    blocks of text that relate to programming concepts and structures

    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
    363
    +0.16
    0.9%
    293
    +0.14
    0.8%
    467
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.16
    0.40
    53
    +0.14
    0.42
    56
    +0.14
    0.11
    Negative Logits
     ):
    -1.57
    enge
    -1.53
    emptyset
    -1.53
    edly
    -1.44
    {(
    -1.44
    createElement
    -1.41
    async
    -1.40
    î
    -1.39
    Errno
    -1.35
     {(
    -1.31
    POSITIVE LOGITS
     slightest
    1.66
     nights
    1.59
    olves
    1.51
     fellows
    1.46
    lands
    1.46
     Tribune
    1.41
     mornings
    1.41
    inals
    1.39
    ony
    1.39
    ourier
    1.34
    Activations Density 4.652%

    No Known Activations