© 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. 26141
    Prev
    Next
    INDEX
    Explanations

    references to bones and bone-related concepts

    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
    93
    +0.15
    0.8%
    376
    +0.14
    0.8%
    156
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    93
    +0.15
    0.02
    439
    +0.14
    0.01
    319
    +0.11
    0.01
    Negative Logits
    Ń
    -2.48
    ¯
    -2.46
    Ĥ
    -2.24
    ı
    -2.17
    §
    -2.08
    Ŀ
    -2.05
    ¼
    -1.99
    ĭ
    -1.94
    ¦
    -1.93
    ³
    -1.87
    POSITIVE LOGITS
     marrow
    1.78
    castle
    1.72
     embargo
    1.67
    hurst
    1.66
    maker
    1.57
    shots
    1.54
    shot
    1.51
    finder
    1.50
    ferroni
    1.49
     chips
    1.48
    Activations Density 0.013%

    No Known Activations