© 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. 31264
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a call to action or instructions

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    173
    +0.15
    0.8%
    128
    +0.12
    0.7%
    348
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.15
    0.38
    151
    +0.12
    0.31
    434
    +0.11
    0.30
    Negative Logits
    º
    -2.33
    ¶
    -2.24
    į
    -2.21
    Ļª
    -2.05
    ´
    -2.04
    ³
    -1.98
    ¬
    -1.96
    IJ
    -1.90
    İ
    -1.88
    ¦
    -1.86
    POSITIVE LOGITS
     NULL
    1.55
    ÑĤо
    1.46
    batim
    1.45
    bin
    1.45
    cember
    1.43
     consider
    1.42
    bard
    1.42
     """
    1.41
    reng
    1.41
    men
    1.39
    Activations Density 1.631%

    No Known Activations