© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 12319
    Prev
    Next
    INDEX
    Explanations

    religious references and terms associated with Islamic teachings and figures

    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
    500
    +0.14
    0.8%
    466
    +0.12
    0.6%
    25
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.14
    0.08
    500
    +0.12
    0.08
    477
    +0.10
    0.09
    Negative Logits
    ↵
    -4.47
    -4.47
    -4.47
    ↵
    -4.47
    -4.47
    ↵↵
    -4.47
    <|outofrange|>
    -4.47
    č↵
    -4.47
    -4.47
    ↵↵
    -4.47
    POSITIVE LOGITS
     Singh
    3.08
     Shah
    2.81
     Khan
    2.78
    ullah
    2.63
     Kumar
    2.61
     Ahmad
    2.59
     Bh
    2.57
     Abdul
    2.57
    ji
    2.56
    abad
    2.53
    Activations Density 0.812%

    No Known Activations