© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 26817
    Prev
    Next
    INDEX
    Explanations

    words specifically related to legal opinions and judgments

    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
    29
    +0.11
    0.6%
    163
    +0.11
    0.6%
    466
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.11
    0.01
    163
    +0.11
    0.01
    116
    +0.11
    0.01
    Negative Logits
    ¼
    -2.15
    ĥ½
    -2.14
    ī
    -2.02
    Į
    -1.97
    Ī
    -1.94
    ·¸
    -1.89
    standing
    -1.81
    ħ
    -1.79
    »
    -1.78
    ´
    -1.71
    POSITIVE LOGITS
    naire
    2.04
    cript
    1.85
    craft
    1.82
    OPLE
    1.81
    ERTY
    1.77
    heet
    1.75
    lists
    1.68
    cards
    1.63
    nel
    1.59
    nell
    1.55
    Activations Density 0.029%

    No Known Activations