© 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. 29497
    Prev
    Next
    INDEX
    Explanations

    references to World War II and its related contexts

    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
    358
    +0.12
    0.7%
    130
    +0.12
    0.7%
    276
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    130
    +0.12
    0.02
    501
    +0.12
    0.02
    254
    +0.11
    0.02
    Negative Logits
    ī
    -4.12
    ³
    -4.05
    Ĵ
    -3.98
    ↵
    -3.86
    ↵↵
    -3.86
    ↵
    -3.86
              ↵
    -3.86
    <|outofrange|>
    -3.86
    ↵↵↵
    -3.86
    -3.86
    POSITIVE LOGITS
    robe
    1.88
    istory
    1.64
    opan
    1.63
    INST
    1.61
    mare
    1.55
    obile
    1.53
    arro
    1.52
    ighter
    1.49
    ama
    1.48
    ield
    1.47
    Activations Density 0.265%

    No Known Activations