© 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. 29835
    Prev
    Next
    INDEX
    Explanations

    references to the pandas data analysis library and its functionalities

    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
    +0.22
    1.2%
    321
    +0.13
    0.7%
    87
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    321
    +0.22
    0.02
    87
    +0.13
    0.01
    392
    +0.12
    0.01
    Negative Logits
    Ķ
    -2.03
    ı
    -1.97
    ¼
    -1.83
    ĵ
    -1.70
    ĥ
    -1.67
    ¦
    -1.66
    ´
    -1.56
    ¯
    -1.51
    §
    -1.49
    ·
    -1.49
    POSITIVE LOGITS
    ncbi
    1.95
    ental
    1.70
    izumab
    1.68
    ://
    1.67
    irez
    1.53
    imab
    1.52
    acea
    1.50
    erve
    1.47
    aurus
    1.47
    '])
    1.47
    Activations Density 0.071%

    No Known Activations