© 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. 8930
    Prev
    Next
    INDEX
    Explanations

    references to processes or systems that involve steps and procedures

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.15
    0.8%
    21
    +0.15
    0.8%
    397
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    359
    +0.15
    0.12
    80
    +0.15
    -0.00
    238
    +0.12
    -0.01
    Negative Logits
    »¿
    -4.35
    ĨĴ
    -4.28
    ģ
    -4.22
    Ļª
    -4.21
    ¿½
    -4.15
    ·¸
    -4.06
    -4.05
      ↵
    -4.05
    -4.05
    -4.05
    POSITIVE LOGITS
     process
    2.81
     steps
    2.77
     procedure
    2.75
     step
    2.58
     execution
    2.53
     Steps
    2.53
     iterative
    2.49
     annealing
    2.43
     tedious
    2.35
     Procedure
    2.34
    Activations Density 3.288%

    No Known Activations