© 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. 13797
    Prev
    Next
    INDEX
    Explanations

    references to prominent news sources and publications

    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
    55
    +0.13
    0.7%
    69
    +0.12
    0.7%
    466
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.13
    0.07
    439
    +0.12
    0.06
    432
    +0.12
    0.06
    Negative Logits
    IJ
    -4.04
    Īĺ
    -4.00
    ĸ
    -3.83
    ĸ´
    -3.81
    -3.77
    -3.77
    -3.77
     ↵
    -3.77
     ↵
    -3.77
    -3.77
    POSITIVE LOGITS
     Magazine
    2.91
     editorial
    2.76
     News
    2.49
     magazine
    2.40
     Tribune
    2.40
     columnist
    2.38
     Herald
    2.37
     Newsp
    2.35
     Daily
    2.32
     correspondent
    2.29
    Activations Density 0.845%

    No Known Activations