© 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. 31012
    Prev
    Next
    INDEX
    Explanations

    instances of the word "announcement."

    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
    +0.21
    1.2%
    376
    +0.19
    1.1%
    365
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    490
    +0.21
    0.02
    206
    +0.19
    0.02
    72
    +0.13
    0.02
    Negative Logits
    ĥ½
    -2.83
    Į
    -2.72
    Ī
    -2.69
    ľĵ
    -2.54
    ĭ
    -2.53
    į
    -2.45
    Ĵ
    -2.41
    ©
    -2.37
    ĵ
    -2.35
    IJ
    -2.31
    POSITIVE LOGITS
     letters
    1.77
    table
    1.68
    tery
    1.67
     period
    1.66
     styles
    1.59
    fix
    1.59
    lists
    1.57
    list
    1.56
     occasions
    1.54
     sequences
    1.54
    Activations Density 0.030%

    No Known Activations