© 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. 26745
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the phrase "the."

    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
    279
    +0.14
    0.8%
    273
    +0.12
    0.7%
    368
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.14
    0.48
    98
    +0.12
    0.21
    228
    +0.12
    0.32
    Negative Logits
    wordpress
    -1.91
    fax
    -1.83
    rendum
    -1.72
    wealth
    -1.69
    idelines
    -1.68
    je
    -1.56
    arty
    -1.55
    dtd
    -1.54
    atory
    -1.54
    liament
    -1.53
    POSITIVE LOGITS
     possible
    1.65
     programmer
    1.64
     again
    1.62
    lan
    1.59
     hel
    1.58
    igator
    1.53
     substrate
    1.51
     inside
    1.47
     researcher
    1.46
     sorts
    1.46
    Activations Density 2.906%

    No Known Activations