© 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. 26058
    Prev
    Next
    INDEX
    Explanations

    sequences and structures involving array brackets

    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
    47
    +0.13
    0.7%
    382
    +0.12
    0.6%
    135
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.13
    0.07
    381
    +0.12
    0.07
    247
    +0.11
    0.07
    Negative Logits
    decoration
    -1.67
    documentclass
    -1.56
    extend
    -1.51
    notation
    -1.50
    hton
    -1.49
    disambiguation
    -1.38
    olve
    -1.37
    reset
    -1.36
    classification
    -1.36
    ctype
    -1.35
    POSITIVE LOGITS
    edly
    1.71
    pires
    1.66
    pered
    1.56
     defects
    1.53
    ibles
    1.52
     (_
    1.52
    ered
    1.46
    ible
    1.44
    eer
    1.41
    avirus
    1.41
    Activations Density 0.062%

    No Known Activations