Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27360
    Prev
    Next
    INDEX
    Explanations

    the word "lifetime"

    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%
    500
    +0.13
    0.8%
    269
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    500
    +0.14
    0.01
    499
    +0.13
    0.01
    269
    +0.12
    0.01
    Negative Logits
     deterg
    -1.59
    'll
    -1.55
     done
    -1.50
     else
    -1.49
     hearts
    -1.47
    idem
    -1.47
    dust
    -1.47
    tics
    -1.43
     knees
    -1.42
     clean
    -1.41
    POSITIVE LOGITS
    ière
    1.67
    ização
    1.66
    chaft
    1.57
    izing
    1.51
    ulating
    1.50
    ulator
    1.47
    osecond
    1.47
    finder
    1.46
    uelle
    1.46
     magazine
    1.45
    Activations Density 0.017%

    No Known Activations