© 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. 13798
    Prev
    Next
    INDEX
    Explanations

    references to legal compliance and regulations related to adoption and ethics

    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
    507
    +0.13
    0.7%
    466
    +0.13
    0.7%
    168
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    168
    +0.13
    0.11
    104
    +0.13
    0.01
    507
    +0.10
    0.04
    Negative Logits
    à±į
    -2.54
    àµį
    -2.14
    à°¿
    -2.06
    à±ģ
    -1.98
    áĢ¬
    -1.97
    à±
    -1.95
    áĢ¯
    -1.95
    à¯į
    -1.94
    à³
    -1.87
    à«ĩ
    -1.84
    POSITIVE LOGITS
     rules
    3.57
     regulations
    3.54
     guidelines
    3.49
     laws
    3.26
     standards
    3.25
     Regulations
    2.88
     requirements
    2.88
     Guidelines
    2.84
     Rules
    2.83
     restrictions
    2.83
    Activations Density 2.033%

    No Known Activations