© 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. 28378
    Prev
    Next
    INDEX
    Explanations

    references to laws, regulations, and amendments related to social or governmental issues

    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
    156
    +0.19
    1.1%
    70
    +0.14
    0.8%
    217
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.19
    0.02
    217
    +0.14
    0.11
    287
    +0.12
    0.12
    Negative Logits
    ĻĤ
    -4.34
    ↵↵
    -4.27
    -4.27
    -4.27
    -4.27
           ↵
    -4.27
    -4.27
          ↵
    -4.27
    ↵
    -4.27
    č↵
    -4.27
    POSITIVE LOGITS
     itself
    2.01
    makers
    1.99
    ors
    1.79
    works
    1.73
    making
    1.68
    **.
    1.65
    ists
    1.61
    ificate
    1.60
     themselves
    1.59
    alta
    1.57
    Activations Density 2.597%

    No Known Activations