© 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. 0-MLP-SM
    11. 31005
    Prev
    Next
    INDEX
    Explanations

    instances of the pronoun "it"

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    450
    +0.11
    0.6%
    308
    +0.10
    0.6%
    27
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.11
    0.21
    185
    +0.10
    0.18
    165
    +0.10
    0.17
    Negative Logits
    wick
    -1.45
    odynamics
    -1.43
    NdEx
    -1.41
    ĨĴ
    -1.39
    áĢ¯
    -1.37
    tte
    -1.37
     matter
    -1.36
    ylated
    -1.35
    anden
    -1.33
    ioned
    -1.30
    POSITIVE LOGITS
    brew
    1.53
    astery
    1.47
     temples
    1.47
    ating
    1.45
     energies
    1.43
    olars
    1.43
    iration
    1.42
     periods
    1.42
     employers
    1.40
    aning
    1.40
    Activations Density 0.740%

    No Known Activations