© 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. 25941
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "broad."

    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
    362
    +0.18
    1.0%
    114
    +0.12
    0.7%
    454
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    114
    +0.18
    0.02
    362
    +0.12
    0.02
    339
    +0.10
    0.02
    Negative Logits
    uka
    -1.62
    ori
    -1.54
    uran
    -1.49
    urop
    -1.48
    urai
    -1.42
    onas
    -1.41
    erald
    -1.40
    aki
    -1.39
    yla
    -1.39
    zy
    -1.38
    POSITIVE LOGITS
    Īĺ
    4.42
    ł
    3.84
    ¢
    3.65
    £
    3.43
    ¥
    3.40
    Ľ
    3.32
    ª
    3.31
    ģ
    3.30
    Ĵ
    3.29
    «
    3.26
    Activations Density 0.371%

    No Known Activations