© 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. 2-MLP-SM
    11. 26403
    Prev
    Next
    INDEX
    Explanations

    references to political figures, specifically Barack Obama and Donald Trump

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    279
    +0.16
    0.9%
    156
    +0.14
    0.8%
    450
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.16
    0.76
    111
    +0.14
    0.75
    71
    +0.12
    0.71
    Negative Logits
    -4.34
     ↵
    -4.34
    ↵↵
    -4.34
    -4.34
    -4.34
    ↵
    -4.34
    ↵
    -4.34
    <|outofrange|>
    -4.34
    ↵
    -4.34
    -4.34
    POSITIVE LOGITS
     compromise
    1.57
    ures
    1.50
     jeopard
    1.43
     irre
    1.43
     disrupt
    1.41
     disruption
    1.41
     hybridization
    1.39
     goodbye
    1.39
     advance
    1.38
     steady
    1.36
    Activations Density 5.290%

    No Known Activations