© 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. 28162
    Prev
    Next
    INDEX
    Explanations

    references to the name "Wil."

    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
    369
    +0.23
    1.3%
    410
    +0.15
    0.9%
    376
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    40
    +0.23
    0.02
    211
    +0.15
    0.02
    359
    +0.13
    0.01
    Negative Logits
     maternal
    -1.53
     fois
    -1.52
    uter
    -1.48
    øre
    -1.41
     magnitude
    -1.41
    itures
    -1.37
    unreadable
    -1.37
    rogens
    -1.36
    xture
    -1.35
    flix
    -1.34
    POSITIVE LOGITS
    igent
    1.60
    fileID
    1.54
    genstein
    1.53
     proved
    1.42
    bourne
    1.39
     awarded
    1.37
    gate
    1.36
     stuck
    1.36
    leys
    1.36
    quito
    1.33
    Activations Density 0.072%

    No Known Activations