© 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. 25435
    Prev
    Next
    INDEX
    Explanations

    instances of the definite article "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
    178
    +0.14
    0.8%
    27
    +0.13
    0.7%
    204
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    27
    +0.14
    0.01
    178
    +0.13
    0.02
    204
    +0.12
    0.01
    Negative Logits
    idth
    -1.74
    itsu
    -1.71
    rico
    -1.70
    ardo
    -1.63
    ime
    -1.61
    buntu
    -1.59
    acio
    -1.57
    ubicin
    -1.56
    amily
    -1.53
    imes
    -1.51
    POSITIVE LOGITS
    <|outofrange|>
    3.94
    3.94
     ↵
    3.94
    ↵
    3.94
    3.94
    ↵
    3.94
    <|outofrange|>
    3.94
    <|outofrange|>
    3.94
    ↵
    3.94
    3.94
    Activations Density 0.128%

    No Known Activations