© 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. 9407
    Prev
    Next
    INDEX
    Explanations

    instances of Indonesian culture and artistry

    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
    411
    +0.17
    1.0%
    163
    +0.14
    0.8%
    74
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    411
    +0.17
    0.06
    30
    +0.14
    0.01
    413
    +0.12
    0.03
    Negative Logits
    ĻĤ
    -2.29
     Hartford
    -1.98
     Wheeler
    -1.73
     Rochester
    -1.73
     Conn
    -1.67
     Wy
    -1.67
     chees
    -1.65
     cheese
    -1.65
    insky
    -1.64
    Īĺ
    -1.64
    POSITIVE LOGITS
     Malaysia
    4.74
     Indonesia
    4.61
     Indonesian
    4.61
     Malaysian
    4.43
     Malay
    4.41
     Singapore
    4.33
     Malays
    4.27
     Indones
    4.13
     Philippines
    4.10
     Philippine
    3.90
    Activations Density 0.851%

    No Known Activations