© 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. 2-MLP-SM
    11. 22806
    Prev
    Next
    INDEX
    Explanations

    words related to legal terminology or court proceedings

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    275
    +0.13
    0.7%
    127
    +0.11
    0.6%
    500
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    275
    +0.13
    0.00
    497
    +0.11
    -0.00
    318
    +0.11
    0.00
    Negative Logits
     pleading
    -1.70
    edly
    -1.59
    alty
    -1.41
    endi
    -1.38
     allegations
    -1.32
    iers
    -1.31
     pleaded
    -1.28
     furious
    -1.27
    ieri
    -1.25
    span
    -1.25
    POSITIVE LOGITS
    ı
    1.79
    Ĵ
    1.79
    º
    1.77
    ±
    1.73
     themselves
    1.68
    Ĭ
    1.66
    IJ
    1.62
     ourselves
    1.62
    ·¸
    1.54
    »
    1.54
    Activations Density 0.184%

    No Known Activations