© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 27288
    Prev
    Next
    INDEX
    Explanations

    military equipment and operations related to warfare

    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
    168
    +0.13
    0.7%
    496
    +0.13
    0.7%
    186
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.13
    -0.01
    234
    +0.13
    0.07
    340
    +0.12
    0.06
    Negative Logits
     blogging
    -1.92
     Pinterest
    -1.78
     blogs
    -1.74
     blog
    -1.73
     cents
    -1.72
     vegan
    -1.61
     Blog
    -1.59
     yoga
    -1.56
     pregnancy
    -1.55
     blogger
    -1.53
    POSITIVE LOGITS
     Aircraft
    2.04
     commanders
    2.03
     deton
    1.93
     weapons
    1.92
     troops
    1.92
     missiles
    1.91
     missile
    1.89
     commander
    1.85
     officers
    1.84
     Engineers
    1.83
    Activations Density 1.632%

    No Known Activations