© 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. 31210
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "second."

    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
    30
    +0.15
    0.8%
    362
    +0.15
    0.8%
    59
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    30
    +0.15
    0.02
    362
    +0.15
    0.01
    239
    +0.11
    0.01
    Negative Logits
    ³
    -2.62
    ĻĤ
    -2.60
    ¸
    -2.48
    Ĥ
    -2.40
    ¹
    -2.33
    ·
    -2.23
    ±
    -2.18
    ģ
    -2.07
    İ
    -2.03
    ¦
    -2.03
    POSITIVE LOGITS
     edition
    1.80
    smen
    1.76
     generations
    1.68
     generation
    1.63
    quart
    1.56
     century
    1.56
     years
    1.53
     inst
    1.53
    iere
    1.46
     centuries
    1.45
    Activations Density 0.554%

    No Known Activations