© 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. 0-MLP-SM
    11. 26862
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the."

    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
    23
    +0.44
    3.4%
    156
    +0.28
    2.2%
    478
    +0.25
    1.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.44
    0.48
    98
    +0.28
    0.21
    228
    +0.25
    0.32
    Negative Logits
    "}](#
    -2.12
    etto
    -1.89
    esan
    -1.80
    ball
    -1.80
    #:
    -1.79
    naire
    -1.76
     mixer
    -1.72
    ÅĽci
    -1.70
    etable
    -1.69
     lottery
    -1.66
    POSITIVE LOGITS
     same
    2.21
     entire
    2.19
     latter
    2.04
    orems
    1.98
    rapeut
    1.95
    ses
    1.92
     most
    1.87
    oretical
    1.86
     brightest
    1.84
     whole
    1.82
    Activations Density 4.821%

    No Known Activations