© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 24576
    Prev
    Next
    INDEX
    Explanations

    instances of parentheses with varying content

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.33
    1.9%
    464
    +0.11
    0.6%
    50
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    50
    +0.33
    0.05
    414
    +0.11
    0.03
    382
    +0.11
    0.05
    Negative Logits
     instant
    -1.68
    rop
    -1.50
    oxin
    -1.30
    imensional
    -1.30
     Academic
    -1.28
    ipart
    -1.21
    ividual
    -1.21
     switch
    -1.19
     alternate
    -1.19
    rated
    -1.19
    POSITIVE LOGITS
    º
    3.02
    Ĩ
    2.94
    ı
    2.86
    IJ
    2.69
    ¿
    2.66
    ¢
    2.65
    ª
    2.61
    ¬
    2.57
    ¥
    2.56
    ½
    2.56
    Activations Density 0.365%

    No Known Activations