© 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. 31249
    Prev
    Next
    INDEX
    Explanations

    repeated phrases emphasizing a sense of collective or shared experience

    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
    9
    +0.13
    0.7%
    253
    +0.11
    0.6%
    328
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    498
    +0.13
    0.11
    184
    +0.11
    0.10
    138
    +0.11
    0.09
    Negative Logits
    Ļª
    -2.02
    ĨĴ
    -1.90
    »¿
    -1.74
    £
    -1.69
    iative
    -1.63
    chell
    -1.60
    nos
    -1.56
    Ĵ
    -1.55
    Ŀ
    -1.47
    ione
    -1.47
    POSITIVE LOGITS
    åºı
    1.40
     vein
    1.39
    raiser
    1.38
     veins
    1.36
    liest
    1.36
     Pradesh
    1.35
    ice
    1.35
    astolic
    1.34
    lift
    1.31
    RSA
    1.29
    Activations Density 0.169%

    No Known Activations