© 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. 1-RES-SM
    11. 28320
    Prev
    Next
    INDEX
    Explanations

    terms related to natural disasters and their impacts

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    276
    +0.14
    0.8%
    156
    +0.14
    0.8%
    59
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.14
    0.04
    56
    +0.14
    0.00
    276
    +0.14
    0.03
    Negative Logits
    ção
    -2.15
    ²
    -1.98
    dk
    -1.70
    Ĭ
    -1.64
    ĺ
    -1.63
    achelor
    -1.63
    athe
    -1.63
    ĸ´
    -1.62
    ções
    -1.62
    ĭ
    -1.62
    POSITIVE LOGITS
    bol
    1.80
    lord
    1.73
     shocks
    1.73
     floods
    1.72
     turbines
    1.69
     storms
    1.65
     surge
    1.64
     rever
    1.63
    shock
    1.63
     fronts
    1.60
    Activations Density 0.459%

    No Known Activations