© 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. 22600
    Prev
    Next
    INDEX
    Explanations

    elements that represent coding or programming syntax, particularly those related to version control and file operations

    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
    23
    +0.17
    1.0%
    375
    +0.15
    0.8%
    27
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.17
    0.06
    82
    +0.15
    0.03
    56
    +0.12
    0.05
    Negative Logits
    ife
    -1.71
    arde
    -1.69
    aml
    -1.65
    ael
    -1.57
    alta
    -1.54
    league
    -1.52
     office
    -1.52
    ymp
    -1.51
    enix
    -1.50
    alle
    -1.48
    POSITIVE LOGITS
     knowing
    1.57
    ties
    1.57
    missibility
    1.50
     wearing
    1.43
     tears
    1.42
    cred
    1.39
     happier
    1.38
     admissibility
    1.38
    Materials
    1.36
    ĻĤ
    1.34
    Activations Density 0.264%

    No Known Activations