© 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. 27928
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Tuesday."

    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
    94
    +0.13
    0.7%
    16
    +0.12
    0.7%
    392
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    94
    +0.13
    0.03
    346
    +0.12
    0.03
    226
    +0.12
    0.02
    Negative Logits
    ·¸
    -5.03
    ↵
    -4.73
    <|outofrange|>
    -4.73
    ↵
    -4.73
    ↵
    -4.73
     ↵
    -4.73
    -4.73
    -4.73
                ↵
    -4.73
    ↵
    -4.73
    POSITIVE LOGITS
    uous
    1.74
    dream
    1.57
    birds
    1.51
    time
    1.51
    ships
    1.50
    vre
    1.50
    ding
    1.49
    eve
    1.47
    baum
    1.47
    nai
    1.44
    Activations Density 0.015%

    No Known Activations