© 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. 25756
    Prev
    Next
    INDEX
    Explanations

    instances of the word "gate" or related terms indicating entrances or barriers

    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
    +0.15
    0.9%
    397
    +0.13
    0.8%
    115
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    194
    +0.15
    0.01
    143
    +0.13
    0.01
    319
    +0.13
    0.01
    Negative Logits
    yx
    -1.83
     garment
    -1.67
     shore
    -1.58
    woke
    -1.48
    keit
    -1.46
    yla
    -1.45
    usa
    -1.42
    cies
    -1.37
    ly
    -1.35
     vigorous
    -1.35
    POSITIVE LOGITS
    keepers
    2.08
    keeper
    1.95
    ways
    1.93
    keeping
    1.87
    holder
    1.84
    face
    1.84
    finder
    1.81
    aments
    1.76
    inator
    1.76
    etting
    1.72
    Activations Density 0.052%

    No Known Activations