© 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. 22381
    Prev
    Next
    INDEX
    Explanations

    phrases related to transactions or agreements

    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
    478
    +0.13
    0.7%
    162
    +0.12
    0.7%
    442
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    104
    +0.13
    0.06
    330
    +0.12
    0.10
    364
    +0.12
    0.07
    Negative Logits
    iph
    -1.54
     verb
    -1.49
    arily
    -1.48
    ariate
    -1.43
    aro
    -1.39
     negatively
    -1.38
    ellar
    -1.37
    ù
    -1.35
     hit
    -1.33
     intellig
    -1.33
    POSITIVE LOGITS
    ħ
    1.56
     mere
    1.45
    ľ
    1.43
     logger
    1.39
     scant
    1.37
    ustr
    1.32
    ±
    1.29
     giant
    1.28
     backdrop
    1.28
     raft
    1.27
    Activations Density 2.172%

    No Known Activations