© 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. 29795
    Prev
    Next
    INDEX
    Explanations

    mentions of specific legal cases and related legal terminology

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    243
    +0.14
    0.8%
    43
    +0.13
    0.7%
    410
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.14
    0.04
    410
    +0.13
    0.04
    243
    +0.13
    0.04
    Negative Logits
    ocin
    -1.48
     honey
    -1.42
    birth
    -1.39
    join
    -1.36
    Ĺ
    -1.34
    omorph
    -1.30
     euros
    -1.27
    erad
    -1.25
    ģ
    -1.25
     infant
    -1.25
    POSITIVE LOGITS
    fficients
    2.01
    enberg
    1.74
    yer
    1.73
    udeau
    1.71
    illard
    1.70
    lee
    1.67
    ème
    1.66
    :`
    1.65
    enzie
    1.58
    imir
    1.56
    Activations Density 0.318%

    No Known Activations