© 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. 24523
    Prev
    Next
    INDEX
    Explanations

    references to conflict or combat

    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
    +0.13
    0.7%
    166
    +0.12
    0.7%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.13
    0.04
    324
    +0.12
    0.03
    166
    +0.12
    0.03
    Negative Logits
    blogger
    -1.94
    Ŀ
    -1.68
    º
    -1.66
    ĨĴ
    -1.65
    ±
    -1.61
     vez
    -1.60
    ´
    -1.59
     born
    -1.58
    ľ
    -1.56
     granted
    -1.55
    POSITIVE LOGITS
    oon
    1.87
    ground
    1.85
    lord
    1.78
    grounds
    1.75
    clock
    1.72
    hammer
    1.64
    case
    1.61
    nut
    1.61
     scenes
    1.57
    rano
    1.57
    Activations Density 0.225%

    No Known Activations