© 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 EvalsExportsinterp-engineNEWAPI 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. 26493
    Prev
    Next
    INDEX
    Explanations

    articles and adjectives associated with technology-related topics

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    225
    +0.14
    0.8%
    408
    +0.12
    0.7%
    167
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    321
    +0.14
    0.24
    98
    +0.12
    0.15
    137
    +0.12
    0.25
    Negative Logits
    ¥
    -5.05
    ī
    -4.91
    «
    -4.84
    İ
    -4.79
    »
    -4.57
    §
    -4.56
    ª
    -4.56
    ĩ
    -4.55
    ®
    -4.54
    Ĭ
    -4.51
    POSITIVE LOGITS
    .^[@
    1.66
    birds
    1.66
    bn
    1.50
     ">
    1.48
    het
    1.42
    pas
    1.37
    âĢī
    1.35
    hole
    1.35
    ctin
    1.33
    nt
    1.31
    Activations Density 1.270%

    No Known Activations