© 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. 31127
    Prev
    Next
    INDEX
    Explanations

    references to mechanisms or systems in scientific, technical, or formal contexts

    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
    156
    +0.25
    1.5%
    376
    +0.13
    0.8%
    365
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    389
    +0.25
    0.01
    297
    +0.13
    0.01
    365
    +0.13
    0.01
    Negative Logits
    ·¸
    -3.46
    ĨĴ
    -3.44
    ³
    -3.39
    Ń
    -3.39
    ¬
    -3.37
    Ļª
    -3.36
    ¯
    -3.28
    ĻĤ
    -3.26
    ĥ½
    -3.21
    -3.21
    POSITIVE LOGITS
    etable
    2.07
    nel
    1.96
    cles
    1.94
    aho
    1.88
    emis
    1.85
    ambers
    1.73
    ilee
    1.73
    oster
    1.73
    ificial
    1.72
    iga
    1.70
    Activations Density 0.010%

    No Known Activations