© 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. 13825
    Prev
    Next
    INDEX
    Explanations

    references to Muslim culture and contemporary societal issues

    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
    +0.38
    2.4%
    306
    +0.34
    2.1%
    348
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    306
    +0.38
    0.14
    307
    +0.34
    0.17
    447
    +0.14
    0.13
    Negative Logits
    urations
    -1.67
    ovic
    -1.54
     thereof
    -1.52
    neys
    -1.52
    hardt
    -1.48
    hers
    -1.47
     pics
    -1.46
    ment
    -1.42
     upside
    -1.42
    rier
    -1.41
    POSITIVE LOGITS
    ↵↵
    4.84
    ↵
    4.84
    ↵
    4.84
    4.84
         ↵
    4.84
     ↵
    4.84
    ↵↵
    4.84
    č↵
    4.84
    4.84
    ↵↵
    4.84
    Activations Density 1.820%

    No Known Activations