© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 22357
    Prev
    Next
    INDEX
    Explanations

    instances of the word "play" and its variations in context to games or gaming activities

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    459
    +0.12
    0.6%
    92
    +0.12
    0.6%
    367
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    311
    +0.12
    0.06
    347
    +0.12
    0.04
    343
    +0.10
    0.05
    Negative Logits
    ongs
    -1.87
    alia
    -1.69
    isma
    -1.53
    oss
    -1.52
    ael
    -1.51
    etica
    -1.46
    olia
    -1.43
    unicode
    -1.42
    ylon
    -1.39
    maven
    -1.39
    POSITIVE LOGITS
     ([*
    1.57
     spectators
    1.43
     spect
    1.40
     clot
    1.37
     stimuli
    1.35
    âĢIJ
    1.32
     elderly
    1.32
     reconsideration
    1.31
    atory
    1.31
    GFR
    1.31
    Activations Density 0.948%

    No Known Activations