© 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. 27903
    Prev
    Next
    INDEX
    Explanations

    instances of the word "shoot."

    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
    372
    +0.11
    0.6%
    489
    +0.11
    0.6%
    178
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    161
    +0.11
    0.02
    160
    +0.11
    0.02
    358
    +0.11
    0.02
    Negative Logits
     gospel
    -1.51
    terday
    -1.50
    noon
    -1.48
    inson
    -1.41
     Diet
    -1.40
    ega
    -1.39
     Genesis
    -1.38
    ette
    -1.38
    eli
    -1.37
    atie
    -1.33
    POSITIVE LOGITS
     interstate
    1.67
     understanding
    1.42
    ther
    1.40
    plan
    1.39
     attention
    1.38
     bargaining
    1.37
    ands
    1.36
    standing
    1.35
     FAA
    1.31
    deck
    1.28
    Activations Density 0.003%

    No Known Activations