© 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. 28449
    Prev
    Next
    INDEX
    Explanations

    the word "where" indicating locations or 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
    409
    +0.14
    0.8%
    432
    +0.12
    0.7%
    413
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.14
    0.02
    364
    +0.12
    0.02
    389
    +0.11
    0.02
    Negative Logits
    ¬
    -3.17
    ŀ
    -3.01
    ↵
    -2.78
    -2.78
    ↵
    -2.78
    <|outofrange|>
    -2.78
    ↵↵
    -2.78
    ↵
    -2.78
    ↵↵
    -2.78
    -2.78
    POSITIVE LOGITS
    mails
    1.59
    birds
    1.54
     area
    1.52
     Caption
    1.51
     variables
    1.51
    isters
    1.49
    amps
    1.49
    ocks
    1.48
    ites
    1.43
    panic
    1.43
    Activations Density 0.007%

    No Known Activations