© 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. 31011
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "or"

    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
    266
    +0.16
    0.9%
    414
    +0.11
    0.6%
    346
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.16
    0.15
    140
    +0.11
    0.15
    511
    +0.11
    0.14
    Negative Logits
    ĥ
    -2.14
    ij
    -1.96
     glance
    -1.70
    esis
    -1.66
    ↵↵
    -1.63
    ↵
    -1.63
    -1.63
    -1.63
    -1.63
     ↵
    -1.63
    POSITIVE LOGITS
    gary
    1.62
    platin
    1.58
    anyl
    1.57
    IFN
    1.55
    documentclass
    1.53
    LET
    1.51
    MER
    1.47
    inux
    1.41
    ="../../../../../../
    1.40
    END
    1.40
    Activations Density 0.255%

    No Known Activations