© 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. 30626
    Prev
    Next
    INDEX
    Explanations

    terms related to flow and fluid dynamics

    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
    144
    +0.15
    0.9%
    156
    +0.15
    0.8%
    484
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    144
    +0.15
    0.02
    484
    +0.15
    0.01
    173
    +0.12
    0.01
    Negative Logits
    mozilla
    -1.78
    amais
    -1.67
    thood
    -1.64
    woke
    -1.62
    ahoma
    -1.60
    unnumbered
    -1.58
     vaccinated
    -1.55
    printStackTrace
    -1.52
    leans
    -1.52
    deal
    -1.52
    POSITIVE LOGITS
     cytometry
    2.45
    chart
    2.37
    ered
    2.08
    ery
    2.05
    charts
    2.02
    Ĵ
    2.01
    Ģ
    2.01
    able
    2.00
    metry
    1.99
    ener
    1.96
    Activations Density 0.090%

    No Known Activations