© 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. 2-MLP-SM
    11. 25120
    Prev
    Next
    INDEX
    Explanations

    repeated phrases of appreciation or similarity

    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
    423
    +0.17
    0.9%
    266
    +0.11
    0.6%
    331
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    423
    +0.17
    0.07
    361
    +0.11
    0.05
    299
    +0.11
    0.04
    Negative Logits
     experience
    -1.50
    chs
    -1.47
    chy
    -1.46
     sockets
    -1.46
    kered
    -1.45
    ured
    -1.44
    ch
    -1.43
    MQ
    -1.41
     decomp
    -1.39
    uitively
    -1.38
    POSITIVE LOGITS
    ioni
    1.75
    ionale
    1.63
    ony
    1.56
    ée
    1.51
     promotion
    1.51
    ieu
    1.50
    ignon
    1.49
    aggio
    1.47
    mlin
    1.46
    Appeal
    1.44
    Activations Density 0.314%

    No Known Activations