© 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. 31250
    Prev
    Next
    INDEX
    Explanations

    specific identifiers or codes related to data records or files

    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
    412
    +0.12
    0.8%
    253
    +0.12
    0.7%
    87
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    412
    +0.12
    0.01
    87
    +0.12
    0.01
    414
    +0.11
    0.01
    Negative Logits
    ¿½
    -1.96
    ¯
    -1.93
     nobody
    -1.77
     close
    -1.75
     half
    -1.74
     neither
    -1.68
     somebody
    -1.68
    quired
    -1.67
     resigned
    -1.61
     none
    -1.58
    POSITIVE LOGITS
    etable
    1.89
    cias
    1.78
    gage
    1.78
    enstein
    1.77
    cie
    1.73
    bsite
    1.72
    eries
    1.70
    heets
    1.69
    erals
    1.68
    skins
    1.65
    Activations Density 0.111%

    No Known Activations