© 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. 0-MLP-SM
    11. 28343
    Prev
    Next
    INDEX
    Explanations

    instances of the word "show."

    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
    220
    +0.11
    0.6%
    50
    +0.11
    0.6%
    320
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    228
    +0.11
    0.06
    298
    +0.11
    0.05
    72
    +0.11
    0.05
    Negative Logits
    Ģ
    -2.01
    Ħ
    -1.93
    ·
    -1.91
    Īĺ
    -1.80
     Western
    -1.69
    Ĩ
    -1.68
    ĥ½
    -1.65
    £
    -1.60
    Ľ
    -1.60
    Ĥ
    -1.59
    POSITIVE LOGITS
     caliber
    1.64
    !(
    1.63
    :]
    1.60
     degree
    1.56
     (_
    1.56
    ilib
    1.51
     torch
    1.50
    ème
    1.49
     degrees
    1.45
    resh
    1.45
    Activations Density 0.025%

    No Known Activations