© 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. 22474
    Prev
    Next
    INDEX
    Explanations

    components related to biochemistry and cell function

    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
    156
    +0.15
    0.8%
    454
    +0.12
    0.7%
    443
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    441
    +0.15
    0.06
    484
    +0.12
    0.05
    368
    +0.11
    0.06
    Negative Logits
    ł
    -1.44
    otta
    -1.37
     tram
    -1.35
     lowering
    -1.33
     Rs
    -1.32
    arettes
    -1.32
    à±ģ
    -1.32
    áĥIJ
    -1.31
    ле
    -1.30
    amma
    -1.30
    POSITIVE LOGITS
    heed
    1.73
    canonical
    1.47
    iper
    1.44
     BASIS
    1.44
     coworkers
    1.39
     vez
    1.38
    emer
    1.37
     other
    1.36
    emis
    1.36
     tire
    1.34
    Activations Density 0.594%

    No Known Activations