© 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. 0-MLP-SM
    11. 31161
    Prev
    Next
    INDEX
    Explanations

    terms related to water sources and their qualities

    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/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
    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.32
    1.9%
    276
    +0.11
    0.7%
    484
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.32
    0.01
    276
    +0.11
    0.01
    319
    +0.11
    0.01
    Negative Logits
    IJ
    -2.53
    ĥ½
    -2.50
    ĭ
    -2.22
    Ĩ
    -2.12
    »
    -2.08
    į
    -2.07
    Ń
    -1.93
    ¯
    -1.91
    ı
    -1.91
    İ
    -1.90
    POSITIVE LOGITS
     regimes
    1.79
    banks
    1.72
    isecond
    1.60
    birds
    1.57
    erals
    1.48
     situations
    1.43
     programmes
    1.41
    fish
    1.40
     shortages
    1.36
    loan
    1.36
    Activations Density 0.007%

    No Known Activations