© 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. 25118
    Prev
    Next
    INDEX
    Explanations

    occurrences of programming languages, specifically Java and Scala

    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
    376
    +0.12
    0.7%
    16
    +0.12
    0.7%
    405
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.12
    0.02
    405
    +0.12
    0.02
    322
    +0.12
    0.01
    Negative Logits
    ĵ
    -2.02
    ·¸
    -2.00
    »
    -1.83
    ©
    -1.79
    ľĵ
    -1.72
    ŀ
    -1.71
    Īĺ
    -1.68
    ±
    -1.64
    ¿½
    -1.63
    ľ
    -1.56
    POSITIVE LOGITS
    emaker
    1.75
    mouth
    1.64
     arsenal
    1.53
    estic
    1.51
     wallet
    1.50
    guns
    1.49
    ariable
    1.49
    fonts
    1.46
     era
    1.43
     calendar
    1.40
    Activations Density 0.011%

    No Known Activations