© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 26734
    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    262
    +0.14
    0.7%
    422
    +0.09
    0.5%
    98
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    262
    +0.14
    0.02
    417
    +0.09
    0.02
    122
    +0.09
    0.01
    Negative Logits
    ĨĴ
    -1.96
    ĩ
    -1.59
     invaded
    -1.56
    ypse
    -1.55
     prosper
    -1.54
    ı
    -1.50
    ¹
    -1.49
    »
    -1.46
    Ļª
    -1.46
    Īĺ
    -1.44
    POSITIVE LOGITS
    cki
    1.66
     onwards
    1.57
     onward
    1.47
    infrared
    1.37
     sunlight
    1.36
    BER
    1.35
    ocene
    1.34
    ).](
    1.32
     CR
    1.32
    sson
    1.31
    Activations Density 0.179%

    No Known Activations