© 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. 15342
    Prev
    Next
    INDEX
    Explanations

    phrases related to copyright or licensing terms

    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
    78
    +0.15
    0.9%
    30
    +0.14
    0.8%
    339
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    30
    +0.15
    0.01
    339
    +0.14
    0.01
    172
    +0.12
    0.01
    Negative Logits
    ately
    -2.07
    ateness
    -1.76
     another
    -1.54
    apine
    -1.53
    IAM
    -1.42
    ace
    -1.42
    ions
    -1.41
    ACE
    -1.37
    oop
    -1.34
    apolis
    -1.34
    POSITIVE LOGITS
     copyright
    1.88
    ģ
    1.79
    1.65
    1.65
    ↵
    1.65
    č↵
    1.65
    ↵  âĢĥ
    1.65
    1.65
    1.65
    ↵
    1.65
    Activations Density 0.044%

    No Known Activations