© 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. 12450
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "of" and variations that indicate possession or relationships between entities

    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
    98
    +0.13
    0.7%
    161
    +0.13
    0.7%
    280
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.13
    0.02
    161
    +0.13
    0.01
    236
    +0.10
    0.01
    Negative Logits
     thereof
    -1.61
    hole
    -1.56
    holes
    -1.45
     tant
    -1.45
     âĢķ
    -1.39
     umbrella
    -1.37
     phenomenon
    -1.37
    æĸ¹æ³ķ
    -1.36
     molecule
    -1.35
    %--
    -1.35
    POSITIVE LOGITS
    §
    1.92
    ¬
    1.90
    ł
    1.89
    ľĵ
    1.88
    ļ
    1.88
     ↵
    1.83
    1.83
    ↵↵
    1.83
    <|outofrange|>
    1.83
    ↵
    1.83
    Activations Density 0.163%

    No Known Activations