© 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. 29474
    Prev
    Next
    INDEX
    Explanations

    the repeated occurrence of the word "it."

    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
    359
    +0.14
    0.8%
    170
    +0.12
    0.7%
    37
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.14
    0.22
    185
    +0.12
    0.18
    165
    +0.12
    0.17
    Negative Logits
     Sciences
    -1.85
    isters
    -1.84
    izes
    -1.75
    arroll
    -1.69
    ize
    -1.54
     outputs
    -1.53
    sembles
    -1.51
    unched
    -1.48
    ization
    -1.44
    unes
    -1.43
    POSITIVE LOGITS
    *.*
    1.46
    ^.
    1.44
    pone
    1.42
    til
    1.42
    *"
    1.41
    ^(
    1.41
    pit
    1.39
    PBS
    1.37
    agon
    1.35
     antagon
    1.34
    Activations Density 0.397%

    No Known Activations