© 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. 28160
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "recently."

    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
    +0.18
    1.0%
    472
    +0.12
    0.7%
    51
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    199
    +0.18
    0.03
    472
    +0.12
    0.03
    337
    +0.12
    0.03
    Negative Logits
    į
    -3.56
    ĨĴ
    -3.52
    IJ
    -3.45
         ↵
    -3.40
    ↵
    -3.40
    ↵↵
    -3.40
    <|outofrange|>
    -3.40
    -3.40
    -3.40
    -3.40
    POSITIVE LOGITS
    eland
    1.50
     extinct
    1.49
    far
    1.46
    phan
    1.42
     deceased
    1.41
     killing
    1.39
    atism
    1.39
    buk
    1.39
     sentiments
    1.36
    rendum
    1.36
    Activations Density 0.395%

    No Known Activations