© 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. 29775
    Prev
    Next
    INDEX
    Explanations

    references to grass-related topics, particularly artificial turf and grass maintenance

    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
    +0.14
    0.8%
    250
    +0.11
    0.6%
    143
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    143
    +0.14
    0.02
    401
    +0.11
    0.01
    128
    +0.10
    0.01
    Negative Logits
    TRODUCTION
    -1.66
     dawn
    -1.55
    woke
    -1.54
     Eve
    -1.49
     happier
    -1.43
    ),$$
    -1.41
     Sidney
    -1.40
     others
    -1.38
     Raleigh
    -1.36
    ubicin
    -1.36
    POSITIVE LOGITS
    roots
    1.90
    bank
    1.89
    notes
    1.77
    balls
    1.70
    core
    1.70
    word
    1.66
    imeters
    1.66
    breaking
    1.65
    words
    1.60
    fish
    1.58
    Activations Density 0.034%

    No Known Activations