© 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. 2-MLP-SM
    11. 25746
    Prev
    Next
    INDEX
    Explanations

    content related to media formats and documents

    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
    387
    +0.14
    0.8%
    156
    +0.13
    0.7%
    238
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    238
    +0.14
    0.03
    14
    +0.13
    0.05
    407
    +0.13
    0.05
    Negative Logits
    ¸
    -2.01
    ĥ½
    -2.00
    ij
    -2.00
    ¬
    -1.95
    ¼
    -1.94
    į
    -1.88
    ĩ
    -1.87
    ¾
    -1.85
    ĭ
    -1.84
    Ģ
    -1.83
    POSITIVE LOGITS
    while
    1.35
     <-
    1.33
    plants
    1.32
     vow
    1.30
    agus
    1.30
    .+
    1.30
    woke
    1.29
     whim
    1.29
    née
    1.28
    Inflater
    1.28
    Activations Density 0.162%

    No Known Activations