© 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. 4-RES-SM
    11. 9094
    Prev
    Next
    INDEX
    Explanations

    legal disclaimers or statements regarding liability and permissions

    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/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
    156
    +0.26
    1.6%
    21
    +0.23
    1.4%
    306
    +0.21
    1.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    450
    +0.26
    0.03
    21
    +0.23
    0.03
    261
    +0.21
    0.04
    Negative Logits
     oli
    -1.41
    uchy
    -1.34
    artan
    -1.31
    idal
    -1.31
    vent
    -1.30
     quarters
    -1.30
    icions
    -1.28
    pler
    -1.28
    atta
    -1.27
    anos
    -1.27
    POSITIVE LOGITS
    Please
    2.03
    WARNING
    1.99
    Arguments
    1.99
    Permission
    1.92
    Copyright
    1.92
    NOTES
    1.90
    If
    1.87
    ================================================================
    1.87
    THIS
    1.85
    Acknowledgments
    1.84
    Activations Density 0.558%

    No Known Activations