© 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. 29618
    Prev
    Next
    INDEX
    Explanations

    references to energy-related topics

    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
    +0.19
    1.1%
    249
    +0.14
    0.8%
    376
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    249
    +0.19
    0.02
    341
    +0.14
    0.02
    219
    +0.14
    0.01
    Negative Logits
    ĥ½
    -2.22
    Ļª
    -2.07
    ³
    -2.00
    Ń
    -1.90
     gay
    -1.80
    µ
    -1.76
    oles
    -1.75
    §
    -1.70
     birth
    -1.62
    pless
    -1.58
    POSITIVE LOGITS
    ======
    1.91
    boat
    1.74
    seek
    1.63
    boats
    1.62
     DISCLAIM
    1.58
    erated
    1.49
    processor
    1.48
     Rating
    1.48
    Bank
    1.47
    Table
    1.46
    Activations Density 0.013%

    No Known Activations