© 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. 29684
    Prev
    Next
    INDEX
    Explanations

    instances of the word "while."

    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
    87
    +0.14
    0.8%
    12
    +0.12
    0.7%
    164
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    104
    +0.14
    0.07
    106
    +0.12
    0.06
    496
    +0.12
    0.06
    Negative Logits
     YES
    -1.53
    \]).
    -1.51
     \-
    -1.48
    .).
    -1.43
     nonsense
    -1.42
     instant
    -1.41
     inherit
    -1.37
     dependencies
    -1.35
     bullshit
    -1.34
    igm
    -1.33
    POSITIVE LOGITS
    okin
    1.63
    ozo
    1.58
    boarding
    1.55
    ---|---
    1.54
    ateurs
    1.53
    pel
    1.50
    elles
    1.47
    entes
    1.43
    ellen
    1.42
    Ä±ÅŁ
    1.41
    Activations Density 0.037%

    No Known Activations