© 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. 26365
    Prev
    Next
    INDEX
    Explanations

    instances of the word "je."

    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
    313
    +0.14
    0.8%
    214
    +0.11
    0.6%
    410
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    313
    +0.14
    0.02
    137
    +0.11
    0.01
    264
    +0.11
    0.01
    Negative Logits
      ↵
    -1.92
     </
    -1.59
    ĵ
    -1.52
     Association
    -1.52
    omitempty
    -1.50
    Ķ
    -1.48
    >';
    -1.42
     '%
    -1.41
    amous
    -1.37
     MERCHANTABILITY
    -1.35
    POSITIVE LOGITS
    ÅĽci
    1.75
    ery
    1.73
    ÅĽ
    1.69
    als
    1.67
    ppo
    1.63
    iko
    1.58
    aho
    1.56
    ruptcy
    1.56
    enn
    1.51
    .
    1.51
    Activations Density 0.013%

    No Known Activations