© 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. 28218
    Prev
    Next
    INDEX
    Explanations

    instances of mathematical operations and their results

    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
    478
    +0.20
    1.1%
    348
    +0.13
    0.7%
    68
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    68
    +0.20
    0.05
    348
    +0.13
    0.04
    66
    +0.13
    0.04
    Negative Logits
    iley
    -1.60
    riz
    -1.58
    ritz
    -1.55
     Hew
    -1.44
    occo
    -1.44
    EMENT
    -1.32
    atories
    -1.31
    um
    -1.30
    holders
    -1.29
     churn
    -1.29
    POSITIVE LOGITS
    ĥ½
    3.18
    Ķ
    2.85
    ³
    2.83
    ĸ´
    2.79
    ¸
    2.70
    ĸ
    2.65
    Ĩ
    2.62
    ĵ
    2.62
    ¥
    2.62
    ¯
    2.58
    Activations Density 0.210%

    No Known Activations