© 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. 2-RES-SM
    11. 12692
    Prev
    Next
    INDEX
    Explanations

    references to Filipino cultural or community elements, particularly in the context of businesses or institutions

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    135
    +0.13
    0.7%
    30
    +0.13
    0.7%
    395
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    135
    +0.13
    0.13
    314
    +0.13
    0.11
    395
    +0.13
    0.12
    Negative Logits
    ³
    -1.88
    ļ
    -1.84
    Ĺ
    -1.79
    ľ
    -1.71
    ĻĤ
    -1.68
    ¼
    -1.68
    ¥
    -1.63
    Ļ
    -1.57
    ±
    -1.56
    ¸
    -1.54
    POSITIVE LOGITS
    )!
    1.69
    %).
    1.52
    roads
    1.52
     themselves
    1.50
     thereof
    1.48
    %)
    1.47
    ialize
    1.45
    ).](
    1.45
    ttes
    1.38
    reads
    1.37
    Activations Density 3.552%

    No Known Activations