© 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. 24943
    Prev
    Next
    INDEX
    Explanations

    references to Maven, a software project management and comprehension tool

    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
    111
    +0.13
    0.7%
    467
    +0.12
    0.7%
    363
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    363
    +0.13
    0.01
    162
    +0.12
    0.01
    111
    +0.11
    0.01
    Negative Logits
     please
    -1.91
     say
    -1.77
     luck
    -1.70
     welcome
    -1.67
     asked
    -1.61
     yes
    -1.59
     suppose
    -1.50
     left
    -1.50
     gonna
    -1.45
     assuming
    -1.44
    POSITIVE LOGITS
    bellum
    1.98
     regimes
    1.74
    hands
    1.68
    pieces
    1.67
    volt
    1.67
     reperto
    1.64
    insky
    1.61
    cav
    1.59
    roads
    1.58
    ruptcy
    1.57
    Activations Density 0.139%

    No Known Activations