© 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. MLP Post
    9. 2-MLP-SM
    11. 25589
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/2-mlp-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_mlp_out
    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
    443
    +0.14
    0.8%
    135
    +0.14
    0.8%
    35
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    135
    +0.14
    0.07
    480
    +0.14
    0.07
    441
    +0.14
    0.05
    Negative Logits
    ostatic
    -1.50
    udo
    -1.37
     encephal
    -1.36
     topological
    -1.29
     ageing
    -1.29
     emerged
    -1.28
     modular
    -1.28
    itness
    -1.26
     arte
    -1.26
    gment
    -1.25
    POSITIVE LOGITS
    Ĵ
    3.61
    £
    3.56
    IJ
    3.49
    3.43
    ↵↵
    3.43
    <|outofrange|>
    3.43
    ↵
    3.43
    ↵
    3.43
    ↵  âĢĥ
    3.43
             ↵
    3.43
    Activations Density 0.744%

    No Known Activations