© 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. 29945
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    390
    +0.15
    0.8%
    250
    +0.13
    0.7%
    480
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    -0.15
    0.00
    1
    -0.13
    0.00
    2
    -0.12
    0.00
    Negative Logits
     protected
    -1.77
    uet
    -1.51
    uple
    -1.49
    elt
    -1.46
    arant
    -1.46
     depend
    -1.40
    or
    -1.39
    avir
    -1.36
    ute
    -1.35
    ivil
    -1.34
    POSITIVE LOGITS
    ¡
    1.67
    ī
    1.66
    ²
    1.64
    Ĵ
    1.59
    Ļª
    1.54
     bargain
    1.45
    ¨
    1.43
    Ļ
    1.40
    Decided
    1.38
     BLAST
    1.36
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.