© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 29301
    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    2
    +0.15
    0.8%
    323
    +0.13
    0.7%
    388
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    -0.15
    0.00
    1
    -0.13
    0.00
    2
    -0.11
    0.00
    Negative Logits
    keit
    -1.61
    hatic
    -1.59
    mi
    -1.59
    ubicin
    -1.56
    hes
    -1.53
    ledge
    -1.50
    outer
    -1.49
    maid
    -1.47
    raint
    -1.45
    inner
    -1.42
    POSITIVE LOGITS
     documenting
    1.72
     Story
    1.55
     caption
    1.44
     remember
    1.44
    heets
    1.42
     page
    1.41
     On
    1.39
     Videos
    1.37
     Figures
    1.34
     pedig
    1.33
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.