© 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. 23580
    Prev
    Next
    INDEX
    Explanations

    phrases related to judicial or legal entities and their 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
    443
    +0.13
    0.7%
    275
    +0.12
    0.6%
    391
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    275
    +0.13
    0.01
    218
    +0.12
    0.02
    323
    +0.10
    0.01
    Negative Logits
    srep
    -1.92
    aceut
    -1.83
    biamo
    -1.79
    ului
    -1.69
    enron
    -1.66
    axon
    -1.59
    ibrary
    -1.58
    ème
    -1.53
    aspase
    -1.51
    icides
    -1.49
    POSITIVE LOGITS
    Ŀ
    3.31
    IJ
    3.07
    Ĺ
    2.98
    Ĭ
    2.98
    «
    2.96
    ¦
    2.96
    ª
    2.93
    Ļ
    2.88
    ¤
    2.84
    ł
    2.82
    Activations Density 0.038%

    No Known Activations