© 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. 31187
    Prev
    Next
    INDEX
    Explanations

    references to fatalities or deaths in various contexts

    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
    365
    +0.13
    0.8%
    376
    +0.12
    0.7%
    156
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    361
    +0.13
    0.01
    387
    +0.12
    0.01
    365
    +0.11
    0.01
    Negative Logits
    ı
    -2.83
    ķ
    -2.67
    ĵ
    -2.64
    Ĵ
    -2.41
    Ķ
    -2.34
    ·¸
    -2.23
    ½
    -2.12
    ¼
    -2.10
    ¿
    -2.10
    ľ
    -2.08
    POSITIVE LOGITS
    igraphy
    1.93
    igraph
    1.92
     ingredient
    1.76
     lamp
    1.74
    ource
    1.64
     detail
    1.61
    icate
    1.59
    iator
    1.57
    ystem
    1.56
    creen
    1.56
    Activations Density 0.011%

    No Known Activations