© 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. 0-MLP-SM
    11. 28986
    Prev
    Next
    INDEX
    Explanations

    the word "the"

    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
    135
    +0.14
    0.8%
    11
    +0.14
    0.8%
    68
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.14
    0.48
    98
    +0.14
    0.21
    228
    +0.12
    0.32
    Negative Logits
     daughter
    -1.70
    aughters
    -1.69
     contacted
    -1.68
     influence
    -1.60
    aughter
    -1.57
    ighed
    -1.57
    olev
    -1.54
    ielle
    -1.44
     visit
    -1.43
     dial
    -1.40
    POSITIVE LOGITS
    ¥
    2.23
    ¯
    1.66
    ³
    1.65
    µ
    1.62
    ĸ
    1.62
    İ
    1.61
    ¼
    1.57
    WORD
    1.56
    Ł
    1.54
    ¦
    1.54
    Activations Density 3.199%

    No Known Activations