© 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. 9899
    Prev
    Next
    INDEX
    Explanations

    phrases related to laws and regulations concerning morality 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
    307
    +0.25
    1.5%
    306
    +0.24
    1.4%
    390
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    390
    +0.25
    0.23
    306
    +0.24
    0.10
    307
    +0.15
    0.21
    Negative Logits
    ĥ½
    -2.12
    »¿
    -1.97
    µ
    -1.94
    Ĥ
    -1.91
    İ
    -1.89
    ĭ
    -1.88
    ħ
    -1.87
    ¿
    -1.84
    ĥ
    -1.83
    °
    -1.82
    POSITIVE LOGITS
     irony
    2.02
     rhet
    1.96
     analogy
    1.84
     paradox
    1.79
     Conclusion
    1.74
     question
    1.71
     argument
    1.70
     interesting
    1.70
     cynical
    1.69
     hypocr
    1.68
    Activations Density 5.667%

    No Known Activations