© 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 EvalsExportsAPI 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. 12801
    Prev
    Next
    INDEX
    Explanations

    mentioned criteria related to diversity and ethnic background

    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
    168
    +0.14
    0.8%
    420
    +0.14
    0.8%
    39
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.14
    0.09
    168
    +0.14
    0.08
    420
    +0.12
    0.06
    Negative Logits
    ľĵ
    -2.98
    ³
    -2.58
    Ļ
    -2.50
    ĻĤ
    -2.44
    Ħ
    -2.43
    ĨĴ
    -2.39
    ·
    -2.39
    Ĭ
    -2.33
    ī
    -2.30
    ľ
    -2.27
    POSITIVE LOGITS
     ethnic
    3.52
     Native
    3.45
     tribes
    3.33
     Indians
    3.30
     Hispanic
    3.28
     ethnicity
    3.23
     ancestry
    3.15
     Africans
    3.09
     tribe
    3.08
     ethn
    3.07
    Activations Density 1.655%

    No Known Activations