© 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. 4-RES-SM
    11. 15109
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to court cases

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    177
    +0.15
    0.8%
    251
    +0.13
    0.7%
    466
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    177
    +0.15
    0.05
    311
    +0.13
    0.04
    155
    +0.13
    0.03
    Negative Logits
    Ĥ¬
    -2.92
    ĨĴ
    -2.63
    Īĺ
    -2.51
    ¾
    -2.50
    Ĺ
    -2.41
    ¥
    -2.28
    ª
    -2.24
    Ĵ
    -2.22
    Ļ
    -2.21
    ij
    -2.19
    POSITIVE LOGITS
     Miller
    2.47
     Richardson
    2.37
     Johnson
    2.33
     Dunn
    2.32
     Jones
    2.31
     Brown
    2.29
     Fowler
    2.28
     McC
    2.25
     Anderson
    2.24
     Mc
    2.23
    Activations Density 0.243%

    No Known Activations