© 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. 28322
    Prev
    Next
    INDEX
    Explanations

    references to dropdown menus or similar UI components

    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
    +0.20
    1.2%
    287
    +0.11
    0.7%
    404
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    287
    +0.20
    0.01
    404
    +0.11
    0.01
    162
    +0.10
    0.01
    Negative Logits
    ĥ½
    -1.87
     wonder
    -1.57
    Ķ
    -1.56
     queer
    -1.56
    ĵ
    -1.53
     hitch
    -1.52
    ĸ´
    -1.50
    ))?
    -1.44
    ³
    -1.44
    ____________
    -1.44
    POSITIVE LOGITS
    sets
    1.98
    gap
    1.76
    pile
    1.72
    set
    1.70
    lists
    1.68
    card
    1.67
    calc
    1.66
    list
    1.62
    gut
    1.62
    stem
    1.61
    Activations Density 0.031%

    No Known Activations