© 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. 2-MLP-SM
    11. 25562
    Prev
    Next
    INDEX
    Explanations

    phrases associated with making up for lost time

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    479
    +0.14
    0.8%
    9
    +0.13
    0.7%
    425
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    479
    +0.14
    0.01
    263
    +0.13
    0.03
    419
    +0.12
    0.02
    Negative Logits
    aceae
    -2.03
    ~*
    -1.69
    .^\[[@
    -1.52
    .[]{
    -1.44
    $.[]{
    -1.43
    []{
    -1.39
    {}\
    -1.39
    \^[
    -1.38
     accounting
    -1.38
    )$\
    -1.37
    POSITIVE LOGITS
    lando
    1.99
    §
    1.96
    »¿
    1.92
    ĸ´
    1.87
    ·¸
    1.86
    °
    1.77
    ¦
    1.76
    ´
    1.74
    naire
    1.67
    umab
    1.65
    Activations Density 0.325%

    No Known Activations