© 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. 13670
    Prev
    Next
    INDEX
    Explanations

    HTML and JavaScript code snippets

    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
    135
    +0.13
    0.7%
    414
    +0.12
    0.7%
    109
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.13
    0.03
    135
    +0.12
    0.05
    365
    +0.12
    0.04
    Negative Logits
     vaccinated
    -1.78
     quarant
    -1.75
     Milwaukee
    -1.75
     CDC
    -1.65
     Sherman
    -1.65
     Dell
    -1.65
     outbreak
    -1.64
     USDA
    -1.64
     Stanton
    -1.62
     Polar
    -1.62
    POSITIVE LOGITS
     JavaScript
    4.27
     javascript
    4.03
     js
    3.98
    js
    3.83
     JS
    3.82
     Javascript
    3.81
    javascript
    3.58
    JavaScript
    3.50
    JS
    3.38
    Script
    3.38
    Activations Density 0.573%

    No Known Activations