© 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. 22542
    Prev
    Next
    INDEX
    Explanations

    references to categories or classifications

    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
    332
    +0.13
    0.7%
    75
    +0.13
    0.7%
    439
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.13
    0.04
    232
    +0.13
    0.03
    231
    +0.12
    0.03
    Negative Logits
    iod
    -1.54
    link
    -1.53
    code
    -1.52
    itive
    -1.49
    tract
    -1.44
    ene
    -1.40
    ledge
    -1.40
    iest
    -1.40
    ylase
    -1.39
    tax
    -1.37
    POSITIVE LOGITS
    ftware
    1.80
    /~
    1.57
    ¿½
    1.52
    alous
    1.51
    /-
    1.46
     Lions
    1.36
     elders
    1.36
    uries
    1.36
     whatever
    1.30
     wearing
    1.29
    Activations Density 0.196%

    No Known Activations