© 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. 28985
    Prev
    Next
    INDEX
    Explanations

    references to battles and conflicts

    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
    304
    +0.15
    0.8%
    184
    +0.12
    0.7%
    100
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    378
    +0.15
    0.03
    166
    +0.12
    0.02
    304
    +0.12
    0.03
    Negative Logits
     whole
    -1.66
    documentclass
    -1.56
     mention
    -1.49
     studies
    -1.47
    atural
    -1.43
    TRODUCTION
    -1.43
     educated
    -1.42
    ates
    -1.42
    atives
    -1.41
    OURCES
    -1.40
    POSITIVE LOGITS
    ground
    2.77
    grounds
    2.65
     scenes
    2.13
     scene
    1.99
    Ļª
    1.95
    oon
    1.94
    front
    1.88
    field
    1.86
    pole
    1.85
    ¡
    1.83
    Activations Density 0.134%

    No Known Activations