© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 22537
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the" and related conjunctions in sentences

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.12
    0.7%
    489
    +0.12
    0.7%
    497
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    423
    +0.12
    0.09
    499
    +0.12
    0.06
    204
    +0.10
    0.04
    Negative Logits
    quired
    -1.82
    pected
    -1.82
     contrasted
    -1.61
     later
    -1.60
    cient
    -1.56
     ensued
    -1.55
     first
    -1.54
    pection
    -1.54
     proposed
    -1.53
     originally
    -1.52
    POSITIVE LOGITS
    «
    2.44
    ↵
    2.37
    <|outofrange|>
    2.37
    <|outofrange|>
    2.37
    č↵
    2.37
    2.37
    <|outofrange|>
    2.37
    ↵↵
    2.37
    ↵  Âł
    2.37
    2.37
    Activations Density 0.786%

    No Known Activations