© 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. 2-MLP-SM
    11. 22455
    Prev
    Next
    INDEX
    Explanations

    legal and regulatory terminology

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    511
    +0.15
    0.9%
    23
    +0.14
    0.8%
    97
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    511
    +0.15
    0.06
    275
    +0.14
    0.02
    86
    +0.13
    0.06
    Negative Logits
     potential
    -1.49
    actin
    -1.45
    riber
    -1.42
    uter
    -1.41
    articles
    -1.39
    reference
    -1.34
    papers
    -1.34
    CSF
    -1.31
    adult
    -1.30
    other
    -1.26
    POSITIVE LOGITS
    ity
    1.79
    cery
    1.68
     Teams
    1.56
    ]{.
    1.56
    ness
    1.55
    keit
    1.51
     Commerce
    1.49
    sible
    1.42
    yaml
    1.42
     anyway
    1.41
    Activations Density 0.458%

    No Known Activations