© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 25448
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to court cases and legal actions

    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
    271
    +0.17
    1.0%
    160
    +0.12
    0.7%
    322
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    112
    +0.17
    0.10
    314
    +0.12
    0.04
    56
    +0.12
    0.11
    Negative Logits
    ®
    -3.31
    ĥ½
    -3.25
    Ħ
    -3.00
    ·
    -2.98
    ¾
    -2.97
    µ
    -2.85
    ³
    -2.83
    Ŀ
    -2.76
    -2.76
    ↵↵
    -2.76
    POSITIVE LOGITS
    else
    1.80
     nobody
    1.72
     awaited
    1.70
    à±ģ
    1.56
    ICE
    1.55
    ylum
    1.54
     everybody
    1.52
    if
    1.51
    eer
    1.50
    à°¿
    1.50
    Activations Density 2.764%

    No Known Activations