© 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. 29245
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Crown" and variations of the word "Crom."

    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
    362
    +0.12
    0.7%
    100
    +0.11
    0.7%
    194
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    194
    +0.12
    0.01
    192
    +0.11
    0.01
    155
    +0.11
    0.01
    Negative Logits
    ĨĴ
    -2.54
    ĥ½
    -2.48
    ¯
    -2.37
    Ļª
    -2.24
    Ń
    -2.22
    ¸
    -2.21
    ķ
    -2.02
    ľ
    -2.00
    ı
    -1.98
    ĩ
    -1.95
    POSITIVE LOGITS
    igan
    1.87
    craft
    1.74
    ionate
    1.73
    stones
    1.68
    bone
    1.68
    stown
    1.67
    ordon
    1.67
    phrase
    1.62
    wort
    1.59
    stone
    1.56
    Activations Density 0.008%

    No Known Activations