© 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. 30592
    Prev
    Next
    INDEX
    Explanations

    instances of the word "repeating" and related terms that suggest an action or theme of recurrence

    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
    +0.18
    1.0%
    247
    +0.14
    0.8%
    156
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    488
    +0.18
    0.01
    255
    +0.14
    0.01
    247
    +0.14
    0.01
    Negative Logits
    ene
    -1.91
    urane
    -1.71
    othe
    -1.64
    ared
    -1.58
    ft
    -1.57
    bered
    -1.50
    asta
    -1.46
    ---|---|---
    -1.46
    ween
    -1.45
    aji
    -1.45
    POSITIVE LOGITS
     patterns
    1.97
     pattern
    1.91
     drills
    1.72
     exercises
    1.68
     topology
    1.58
     routines
    1.56
     sequences
    1.54
    plement
    1.51
     cycle
    1.42
     puzzles
    1.41
    Activations Density 0.013%

    No Known Activations