© 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. 24049
    Prev
    Next
    INDEX
    Explanations

    terms associated with corporate scandals and financial misconduct

    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
    169
    +0.15
    0.9%
    71
    +0.14
    0.8%
    111
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.15
    0.03
    410
    +0.14
    0.02
    321
    +0.14
    0.01
    Negative Logits
     evaluated
    -1.61
     defined
    -1.61
     respectively
    -1.59
     differentiable
    -1.58
     shown
    -1.58
     difference
    -1.54
     assessed
    -1.52
    rd
    -1.52
    ths
    -1.51
     tuned
    -1.48
    POSITIVE LOGITS
    IFIC
    1.91
    ENRON
    1.85
    ãĥ³ãĥĪ
    1.83
    abad
    1.81
    åĬ¡
    1.77
    holm
    1.76
    anese
    1.75
    æ¥Ń
    1.74
    ollah
    1.72
    à±į
    1.72
    Activations Density 0.070%

    No Known Activations