© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 25636
    Prev
    Next
    INDEX
    Explanations

    references to mortality or death

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.27
    1.7%
    375
    +0.13
    0.8%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    375
    +0.27
    0.01
    361
    +0.13
    0.01
    204
    +0.12
    0.01
    Negative Logits
    ĥ½
    -2.21
    ½
    -2.07
    ĸ´
    -2.05
    ı
    -2.01
    ĵ
    -1.96
    ¿
    -1.94
    ī
    -1.87
    Ŀ
    -1.67
    ·¸
    -1.66
    ķ
    -1.64
    POSITIVE LOGITS
     situation
    1.74
     system
    1.72
    igraph
    1.65
     rates
    1.58
     prevention
    1.55
     aside
    1.51
     ratio
    1.50
     booth
    1.50
     area
    1.49
     areas
    1.47
    Activations Density 0.008%

    No Known Activations