© 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. 8867
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    153
    +0.14
    0.8%
    187
    +0.12
    0.6%
    208
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    -0.14
    0.00
    1
    -0.12
    0.00
    2
    -0.12
    0.00
    Negative Logits
    azine
    -1.78
    amycin
    -1.73
    ensis
    -1.70
    ://
    -1.66
    uously
    -1.65
    eless
    -1.65
    ennis
    -1.61
    ently
    -1.61
    oto
    -1.60
    atinib
    -1.59
    POSITIVE LOGITS
    ¢
    3.37
    IJ
    3.23
    ĻĤ
    3.07
    ĩ
    2.87
    ĸ
    2.86
    ħ
    2.85
    ļ
    2.79
    ²
    2.75
    ®
    2.73
    ¬
    2.72
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.