© 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 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. 28639
    Prev
    Next
    INDEX
    Explanations

    specific patterns in data structures or syntax

    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
    392
    +0.13
    0.7%
    429
    +0.12
    0.7%
    376
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.13
    0.01
    429
    +0.12
    0.01
    506
    +0.11
    0.01
    Negative Logits
     myself
    -1.80
    )?
    -1.80
     peace
    -1.75
     me
    -1.72
     yourself
    -1.69
     #{
    -1.67
     simultaneously
    -1.57
     gonna
    -1.54
    quo
    -1.53
     alive
    -1.51
    POSITIVE LOGITS
    tip
    1.84
    chart
    1.78
    tailed
    1.75
    sight
    1.72
    mouth
    1.68
    nikov
    1.68
    sburg
    1.57
    smen
    1.55
    lane
    1.53
     (\<
    1.52
    Activations Density 0.050%

    No Known Activations