© 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. 26918
    Prev
    Next
    INDEX
    Explanations

    instances of the word "matched."

    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
    +0.23
    1.4%
    376
    +0.18
    1.1%
    148
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    487
    +0.23
    0.01
    40
    +0.18
    0.01
    122
    +0.15
    0.01
    Negative Logits
    ĥ½
    -2.18
    woke
    -1.98
    llo
    -1.95
    §
    -1.90
    ®
    -1.90
    ĥ
    -1.89
    ¹
    -1.75
    dered
    -1.66
    ĵ
    -1.65
    Ĥ
    -1.65
    POSITIVE LOGITS
     ones
    1.93
     area
    1.79
     areas
    1.65
    orno
    1.57
    bag
    1.55
     medium
    1.52
     positions
    1.47
    river
    1.45
    wick
    1.42
     possession
    1.40
    Activations Density 0.009%

    No Known Activations