© 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. 26464
    Prev
    Next
    INDEX
    Explanations

    the usage of the term "lady."

    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
    181
    +0.12
    0.7%
    296
    +0.12
    0.7%
    367
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    181
    +0.12
    0.01
    293
    +0.12
    0.01
    296
    +0.12
    0.01
    Negative Logits
     spoken
    -1.87
    inely
    -1.62
     called
    -1.57
     pronounced
    -1.57
     containing
    -1.56
     fitted
    -1.54
     taken
    -1.53
     traced
    -1.52
     considered
    -1.50
     arranged
    -1.48
    POSITIVE LOGITS
    ĻĤ
    2.26
    holm
    2.11
    castle
    1.90
    casters
    1.85
    caster
    1.81
    aho
    1.79
    ruptcy
    1.75
    º
    1.74
    kowski
    1.72
    fors
    1.72
    Activations Density 0.011%

    No Known Activations