© 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 EvalsExportsAPI 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. 10901
    Prev
    Next
    INDEX
    Explanations

    references to historical conflicts and agreements

    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
    8
    +0.13
    0.7%
    41
    +0.12
    0.7%
    57
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    41
    +0.13
    0.04
    413
    +0.12
    0.03
    340
    +0.12
    0.02
    Negative Logits
    ĻĤ
    -2.90
    «
    -2.28
    ľ
    -2.27
    ĨĴ
    -2.23
      ↵
    -2.15
    -2.15
    č↵č↵
    -2.15
    ↵
    -2.15
       ↵
    -2.15
    ↵
    -2.15
    POSITIVE LOGITS
     Ireland
    4.60
     Dublin
    4.32
     Irish
    4.30
     Cork
    3.94
     Belfast
    3.92
    reland
    3.89
    Irish
    3.88
     Celtic
    3.17
     SDL
    2.92
     Scotland
    2.92
    Activations Density 0.574%

    No Known Activations