© 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. 26333
    Prev
    Next
    INDEX
    Explanations

    references to the Northwest region

    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
    +0.18
    1.0%
    362
    +0.13
    0.8%
    445
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    259
    +0.18
    0.01
    445
    +0.13
    0.01
    181
    +0.12
    0.01
    Negative Logits
    ching
    -1.98
    iorari
    -1.64
    ção
    -1.62
    ters
    -1.54
    ween
    -1.53
    ries
    -1.53
    cluding
    -1.51
    actic
    -1.49
    ĥ½
    -1.45
    rian
    -1.43
    POSITIVE LOGITS
    craft
    1.73
    fried
    1.67
    leen
    1.59
    oft
    1.56
    ilee
    1.48
    blank
    1.47
    \$
    1.46
     refers
    1.45
    must
    1.43
     defines
    1.40
    Activations Density 0.767%

    No Known Activations