© 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. 31006
    Prev
    Next
    INDEX
    Explanations

    repeated occurrences of the substring "BU"

    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
    444
    +0.12
    0.7%
    246
    +0.12
    0.7%
    410
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    134
    +0.12
    0.02
    16
    +0.12
    0.02
    375
    +0.12
    0.01
    Negative Logits
    matically
    -1.69
     diseased
    -1.59
     mean
    -1.52
    nez
    -1.50
    izing
    -1.49
    hip
    -1.47
     others
    -1.46
     slightest
    -1.46
     latter
    -1.44
     attenuated
    -1.44
    POSITIVE LOGITS
    ģ
    1.97
    ppo
    1.80
    ruptcy
    1.78
    vre
    1.68
    culus
    1.68
    enstein
    1.66
    illard
    1.66
    lei
    1.65
    ½
    1.62
    ®
    1.57
    Activations Density 0.012%

    No Known Activations