© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 26686
    Prev
    Next
    INDEX
    Explanations

    instances of assignment statements in code

    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
    156
    +0.32
    1.8%
    408
    +0.18
    1.0%
    23
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    279
    +0.32
    0.04
    408
    +0.18
    0.03
    56
    +0.14
    0.04
    Negative Logits
    Ł
    -2.08
    º
    -2.02
    ª
    -1.92
    ĨĴ
    -1.79
    IJ
    -1.74
    ĸ
    -1.73
    Ń
    -1.71
    ĥ½
    -1.70
    ¬
    -1.68
    ı
    -1.66
    POSITIVE LOGITS
     inferred
    1.61
     origin
    1.61
    atto
    1.46
     corpus
    1.41
    ellate
    1.37
     incidence
    1.36
     operator
    1.36
     observed
    1.35
     excited
    1.34
    ylum
    1.30
    Activations Density 0.180%

    No Known Activations