© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 25427
    Prev
    Next
    INDEX
    Explanations

    phrases related to concentration levels of substances

    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
    108
    +0.13
    0.7%
    61
    +0.11
    0.6%
    435
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.13
    0.01
    168
    +0.11
    0.01
    341
    +0.11
    0.02
    Negative Logits
    ¢
    -1.74
    ]):
    -1.59
    »
    -1.56
    enden
    -1.55
    rial
    -1.53
    alf
    -1.52
    gui
    -1.51
     settings
    -1.51
    )?
    -1.48
    zzo
    -1.48
    POSITIVE LOGITS
     AUTH
    1.81
     POSS
    1.54
     AUTHOR
    1.46
     MAP
    1.42
     luck
    1.42
     YES
    1.39
     Pinterest
    1.35
     ARI
    1.34
     bloss
    1.34
     cannabis
    1.30
    Activations Density 0.131%

    No Known Activations