© 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. 26614
    Prev
    Next
    INDEX
    Explanations

    equality signs and associated operations in programming or mathematical expressions

    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
    +0.19
    1.1%
    407
    +0.13
    0.8%
    414
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    407
    +0.19
    0.06
    414
    +0.13
    0.07
    480
    +0.13
    0.05
    Negative Logits
     (`
    -1.75
    's
    -1.71
    _
    -1.65
    taire
    -1.58
    \$
    -1.58
    =
    -1.49
    ename
    -1.45
    ;
    -1.45
    ously
    -1.45
    =${
    -1.44
    POSITIVE LOGITS
    testing
    1.87
    rog
    1.83
     blame
    1.63
     dangers
    1.55
     him
    1.45
    dered
    1.44
     new
    1.43
    touch
    1.42
    isex
    1.42
    rous
    1.40
    Activations Density 0.057%

    No Known Activations