© 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. 1-RES-SM
    11. 24018
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and court proceedings

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    278
    +0.14
    0.8%
    373
    +0.12
    0.7%
    282
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    278
    +0.14
    0.05
    373
    +0.12
    0.04
    149
    +0.12
    0.04
    Negative Logits
    ersion
    -1.74
     mapping
    -1.69
    Ĵ
    -1.67
    Generated
    -1.65
    ...]
    -1.62
    Ľ
    -1.61
    gow
    -1.60
    coding
    -1.60
     generated
    -1.59
     mappings
    -1.57
    POSITIVE LOGITS
    inois
    1.83
     constitutionally
    1.72
     lit
    1.72
     unconstitutional
    1.71
     fiduciary
    1.71
     impe
    1.67
     plaintiffs
    1.64
     pursuant
    1.62
     petition
    1.60
     constitutional
    1.60
    Activations Density 0.585%

    No Known Activations