© 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. 15380
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references related to appellate court decisions

    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
    71
    +0.15
    0.8%
    27
    +0.14
    0.8%
    168
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    168
    +0.15
    0.05
    75
    +0.14
    0.02
    27
    +0.14
    0.04
    Negative Logits
    ively
    -1.56
    ries
    -1.48
    escap
    -1.45
    aster
    -1.43
    gtk
    -1.43
    imize
    -1.43
    imental
    -1.40
    ben
    -1.36
    ric
    -1.35
    autre
    -1.33
    POSITIVE LOGITS
    ľĵ
    3.83
    Į
    3.78
    ²
    3.76
    «
    3.62
    ĩ
    3.55
    ĸ
    3.54
    ↵  ↵
    3.48
    ↵Č
    3.48
    <|outofrange|>
    3.48
    <|outofrange|>
    3.48
    Activations Density 0.240%

    No Known Activations