© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 25141
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to court cases and claims

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    116
    +0.15
    0.9%
    276
    +0.11
    0.7%
    410
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.01
    82
    +0.11
    0.01
    322
    +0.10
    0.01
    Negative Logits
    ³
    -2.96
    Ī
    -2.80
    ·¸
    -2.64
    ¿½
    -2.63
    ħ
    -2.61
    ´
    -2.60
    ¬
    -2.58
    Ĩ
    -2.56
    į
    -2.56
    ĥ
    -2.51
    POSITIVE LOGITS
    nell
    2.13
    ERTY
    2.09
    ruptcy
    1.99
    naire
    1.84
    notes
    1.71
    elist
    1.68
    skins
    1.67
    pieces
    1.67
    sheet
    1.66
    lege
    1.65
    Activations Density 0.018%

    No Known Activations