© 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. 29760
    Prev
    Next
    INDEX
    Explanations

    mentions of processing tasks or activities

    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
    156
    +0.17
    1.0%
    451
    +0.12
    0.7%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    451
    +0.17
    0.01
    282
    +0.12
    0.02
    102
    +0.12
    0.02
    Negative Logits
    ĥ½
    -4.38
    Į
    -3.79
    ŀ
    -3.61
    ¼
    -3.57
    §
    -3.51
    ½
    -3.45
    ı
    -3.35
    ¾
    -3.34
    Ī
    -3.26
    ¹
    -3.26
    POSITIVE LOGITS
     processor
    1.84
     done
    1.73
     center
    1.70
     maker
    1.67
     capacity
    1.66
     machine
    1.60
     which
    1.58
     equipment
    1.58
     job
    1.57
     thereof
    1.57
    Activations Density 0.088%

    No Known Activations