© 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. 30739
    Prev
    Next
    INDEX
    Explanations

    instances of the word "underwent" and its variations

    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
    +0.24
    1.4%
    148
    +0.20
    1.2%
    156
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.24
    0.01
    396
    +0.20
    0.01
    50
    +0.14
    0.01
    Negative Logits
    hurst
    -1.59
    icum
    -1.58
    MOESM
    -1.55
    view
    -1.52
    еÑģк
    -1.50
    flix
    -1.47
    ermost
    -1.46
    boards
    -1.42
    holders
    -1.41
    ":"",
    -1.39
    POSITIVE LOGITS
     congression
    1.68
     retrograde
    1.65
     defe
    1.54
    ör
    1.41
     missing
    1.39
    nant
    1.34
     detach
    1.31
    ethod
    1.31
    antom
    1.29
    orate
    1.28
    Activations Density 0.014%

    No Known Activations