© 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. 25398
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Anthony."

    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
    156
    +0.26
    1.5%
    369
    +0.16
    0.9%
    211
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    211
    +0.26
    0.02
    332
    +0.16
    0.01
    251
    +0.14
    0.01
    Negative Logits
    ĥ½
    -2.40
    Ļª
    -2.38
    ı
    -2.12
    ĵ
    -2.11
    Ń
    -2.05
    ĨĴ
    -1.97
    ¼
    -1.97
    ĺ
    -1.94
    ¿
    -1.94
    ¿½
    -1.88
    POSITIVE LOGITS
    issance
    1.51
     sequenced
    1.48
     Awards
    1.43
    aho
    1.42
    fried
    1.41
    stown
    1.40
     Award
    1.39
    stadt
    1.38
    hole
    1.38
    veolar
    1.38
    Activations Density 0.018%

    No Known Activations