© 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. Residuals
    9. 2-RES-SM
    11. 26186
    Prev
    Next
    INDEX
    Explanations

    terms related to legal or judicial language

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-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_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    198
    +0.16
    0.9%
    235
    +0.13
    0.8%
    345
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    345
    +0.16
    0.08
    279
    +0.13
    0.07
    198
    +0.13
    0.07
    Negative Logits
    ·
    -3.19
    ĭ
    -3.15
    ¸
    -3.02
    ħ
    -3.00
    į
    -2.85
    Ŀ
    -2.84
    Ļ
    -2.77
    ĵ
    -2.76
    ĥ½
    -2.72
    ı
    -2.70
    POSITIVE LOGITS
     facto
    1.52
    igg
    1.44
     aeruginosa
    1.39
    igger
    1.39
    itably
    1.38
    arest
    1.37
    iece
    1.35
    hurst
    1.34
    ooth
    1.30
    gor
    1.30
    Activations Density 0.777%

    No Known Activations