© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 28509
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to legal dismissals

    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
    43
    +0.11
    0.6%
    250
    +0.11
    0.6%
    226
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    103
    +0.11
    0.02
    24
    +0.11
    0.02
    59
    +0.11
    0.02
    Negative Logits
     ligation
    -1.68
    documentclass
    -1.43
    unners
    -1.36
    ](
    -1.32
    oire
    -1.31
    tailed
    -1.31
    âĪ¼
    -1.29
    dee
    -1.29
    $]{};
    -1.29
    sen
    -1.28
    POSITIVE LOGITS
     charges
    1.72
     options
    1.54
    charg
    1.48
    enses
    1.46
    ...)
    1.45
     order
    1.43
    ,...
    1.42
    ert
    1.38
     disbelief
    1.38
    icing
    1.37
    Activations Density 0.077%

    No Known Activations