© 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 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. 28736
    Prev
    Next
    INDEX
    Explanations

    the word "gu" in various contexts or usages

    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
    369
    +0.17
    1.0%
    355
    +0.15
    0.9%
    194
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    355
    +0.17
    0.02
    194
    +0.15
    0.01
    310
    +0.15
    0.01
    Negative Logits
    ching
    -1.58
     achievable
    -1.51
    $$
    -1.49
    nez
    -1.47
     coming
    -1.44
    boarding
    -1.44
     forthcoming
    -1.43
     commission
    -1.42
    laid
    -1.41
    rium
    -1.40
    POSITIVE LOGITS
    erre
    2.15
    anine
    2.00
    ĺ
    1.81
    ppo
    1.80
    Ī
    1.77
    Ľ
    1.71
    ierno
    1.71
    agi
    1.67
    illard
    1.66
    į
    1.66
    Activations Density 0.171%

    No Known Activations