© 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. 31262
    Prev
    Next
    INDEX
    Explanations

    words or terms indicating critical failure or essential status

    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
    376
    +0.13
    0.7%
    276
    +0.12
    0.7%
    11
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.13
    0.02
    40
    +0.12
    0.01
    486
    +0.12
    0.01
    Negative Logits
    ³
    -2.00
    Ĥ¬
    -1.88
    ½
    -1.75
    »
    -1.68
    Ī
    -1.57
    Ļ
    -1.50
    hip
    -1.50
    ı
    -1.48
    Ĺ
    -1.45
    ĸ´
    -1.44
    POSITIVE LOGITS
    ities
    1.91
     mistakes
    1.81
    dehyde
    1.81
     objections
    1.71
    ités
    1.67
    ists
    1.66
    ening
    1.63
    anguage
    1.63
    falls
    1.62
     errors
    1.60
    Activations Density 2.060%

    No Known Activations