© 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. 25152
    Prev
    Next
    INDEX
    Explanations

    references to code structures or syntax elements

    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
    383
    +0.14
    0.8%
    409
    +0.14
    0.8%
    255
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    495
    +0.14
    0.05
    35
    +0.14
    0.05
    421
    +0.12
    0.05
    Negative Logits
    £
    -1.79
    ĸ
    -1.78
    eni
    -1.75
    ¢
    -1.68
    ¨
    -1.63
    §
    -1.61
    Ń
    -1.57
    Ļ
    -1.52
    ishers
    -1.47
    Ĵ
    -1.47
    POSITIVE LOGITS
     argu
    1.67
    xit
    1.57
    hurst
    1.54
     orally
    1.49
    linger
    1.47
     MERCHANTABILITY
    1.45
     reflections
    1.44
     testified
    1.41
     tasted
    1.40
     privately
    1.40
    Activations Density 0.066%

    No Known Activations