© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27663
    Prev
    Next
    INDEX
    Explanations

    instances of the word "when."

    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
    376
    +0.15
    0.8%
    478
    +0.13
    0.7%
    174
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    174
    +0.15
    0.07
    154
    +0.13
    0.08
    112
    +0.11
    0.08
    Negative Logits
     scrape
    -1.56
     Rhodes
    -1.54
    ray
    -1.50
    ipes
    -1.50
    usc
    -1.49
    elij
    -1.49
     remember
    -1.46
    membrane
    -1.43
    iston
    -1.40
     Scotia
    -1.40
    POSITIVE LOGITS
    ĥ½
    3.31
    ı
    3.15
    Ĩ
    3.03
    Ĥ
    2.83
    ¤
    2.69
    ¹
    2.67
    Ļ
    2.65
    ·
    2.63
    Ģ
    2.50
    ī
    2.49
    Activations Density 0.126%

    No Known Activations