© 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. 23705
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal judgments or court procedures

    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
    47
    +0.16
    0.9%
    156
    +0.15
    0.8%
    129
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    467
    +0.16
    0.02
    503
    +0.15
    0.03
    386
    +0.10
    0.01
    Negative Logits
    áĢ¯
    -1.77
     Facts
    -1.75
    ureus
    -1.70
     candid
    -1.67
    áĢº
    -1.66
    unnumbered
    -1.66
    à±
    -1.54
     Fact
    -1.50
     facts
    -1.42
    izumab
    -1.40
    POSITIVE LOGITS
    ço
    1.63
    ļ
    1.61
     control
    1.48
    '):
    1.47
    /'
    1.42
    ?).
    1.41
    oil
    1.41
    notations
    1.41
    sense
    1.39
    ync
    1.38
    Activations Density 0.112%

    No Known Activations