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

    Neuronpedia

    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. 0-MLP-SM
    11. 26788
    Prev
    Next
    INDEX
    Explanations

    terminology related to design interaction and user experience concepts

    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
    478
    +0.18
    1.0%
    203
    +0.14
    0.8%
    111
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.18
    0.01
    298
    +0.14
    0.01
    90
    +0.14
    0.01
    Negative Logits
    aste
    -1.90
    umes
    -1.81
    illard
    -1.77
    PLIED
    -1.70
    icki
    -1.61
    aska
    -1.59
    omonas
    -1.56
    ipel
    -1.52
    :&
    -1.49
    ,
    -1.47
    POSITIVE LOGITS
    Ļª
    2.73
    º
    2.56
    ¯
    2.29
    ¬
    2.23
    ¥
    2.15
    ¶
    2.13
    ľ
    2.08
    ĸ´
    1.93
      ↵
    1.93
    ↵
    1.93
    Activations Density 0.029%

    No Known Activations