© 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. 27156
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the word "the" in various contexts

    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
    466
    +0.12
    0.7%
    330
    +0.12
    0.6%
    150
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.12
    0.48
    98
    +0.12
    0.21
    228
    +0.11
    0.32
    Negative Logits
    ↵↵
    -2.83
    č↵
    -2.83
    <|outofrange|>
    -2.83
       ↵
    -2.83
    ↵
    -2.83
    č↵
    -2.83
    ↵
    -2.83
    -2.83
    ↵
    -2.83
    <|outofrange|>
    -2.83
    POSITIVE LOGITS
     recogn
    1.53
     cher
    1.53
     reck
    1.52
    atives
    1.50
     admire
    1.50
    EL
    1.49
    ().
    1.49
     desperately
    1.48
    ITED
    1.44
     recognise
    1.44
    Activations Density 2.930%

    No Known Activations