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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 30515
    Prev
    Next
    INDEX
    Explanations

    instances of the word "suddenly."

    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
    156
    +0.21
    1.2%
    376
    +0.18
    1.0%
    23
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    63
    +0.21
    0.01
    84
    +0.18
    0.01
    257
    +0.14
    0.01
    Negative Logits
    ymphony
    -1.63
    SEA
    -1.58
     typically
    -1.58
    ibles
    -1.55
    :`
    -1.54
    athon
    -1.53
    ressor
    -1.49
    rie
    -1.47
    ware
    -1.46
    lor
    -1.45
    POSITIVE LOGITS
    ?’
    1.39
     GENERATED
    1.34
     deceased
    1.32
    ocortic
    1.32
     extinct
    1.31
     Opposition
    1.30
     cracking
    1.29
     deleting
    1.28
    ortality
    1.27
     ration
    1.27
    Activations Density 0.017%

    No Known Activations