© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 25246
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the word "we."

    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
    388
    +0.14
    0.8%
    150
    +0.14
    0.8%
    495
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    498
    +0.14
    0.11
    184
    +0.14
    0.09
    138
    +0.11
    0.09
    Negative Logits
    ¿½
    -3.45
    ·¸
    -3.36
    ³
    -3.20
    ĭ
    -2.88
    °
    -2.86
    ¥
    -2.86
    ¿
    -2.74
    ¶
    -2.74
    ¹
    -2.73
    ¤
    -2.71
    POSITIVE LOGITS
     experienced
    1.71
     owed
    1.62
     encountered
    1.60
     existed
    1.55
     ordained
    1.55
    recognized
    1.53
    chitz
    1.52
     deported
    1.50
     settled
    1.49
     rewarded
    1.48
    Activations Density 0.167%

    No Known Activations