© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 30268
    Prev
    Next
    INDEX
    Explanations

    references to ships and maritime activities

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    +0.18
    1.1%
    173
    +0.13
    0.8%
    46
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    173
    +0.18
    0.02
    56
    +0.13
    -0.00
    80
    +0.12
    0.03
    Negative Logits
    apine
    -2.04
    ĥ½
    -1.91
    ¼
    -1.89
    »
    -1.83
    ferential
    -1.81
    ļ
    -1.78
     mucosal
    -1.68
    Ħ
    -1.62
    ferentially
    -1.60
    ¹
    -1.60
    POSITIVE LOGITS
    boats
    2.31
    boat
    2.21
    yards
    2.10
     aboard
    2.06
    manship
    1.91
    smen
    1.90
    ship
    1.85
    yard
    1.83
     ships
    1.75
     sailing
    1.75
    Activations Density 0.295%

    No Known Activations