© 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. 28191
    Prev
    Next
    INDEX
    Explanations

    repeated usage of the pronoun "he."

    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
    8
    +0.14
    0.8%
    194
    +0.14
    0.7%
    416
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    500
    +0.14
    0.11
    248
    +0.14
    0.09
    295
    +0.11
    0.09
    Negative Logits
    word
    -1.72
    Ŀ
    -1.53
    source
    -1.48
    MSC
    -1.42
    amino
    -1.38
    die
    -1.37
    Austral
    -1.37
    sentence
    -1.37
    molecular
    -1.37
    rut
    -1.35
    POSITIVE LOGITS
    ctions
    1.71
     lasts
    1.62
     confidentiality
    1.61
     privacy
    1.60
     lasted
    1.59
     privileges
    1.50
     itself
    1.50
     dresses
    1.49
    asures
    1.48
     Declaration
    1.46
    Activations Density 0.144%

    No Known Activations