© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 28307
    Prev
    Next
    INDEX
    Explanations

    references to bathrooms and toilets

    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
    156
    +0.17
    1.0%
    148
    +0.14
    0.8%
    102
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.17
    0.02
    184
    +0.14
    0.02
    319
    +0.11
    0.01
    Negative Logits
    ĨĴ
    -2.32
    §
    -2.22
    ³
    -2.21
    ¹
    -2.21
    ĥ½
    -2.17
                                   
    -2.06
    ↵                                     
    -2.06
    č↵           
    -2.06
    ↵↵    
    -2.06
                           
    -2.06
    POSITIVE LOGITS
    ichlet
    1.68
    ENTIAL
    1.55
    "}](#
    1.53
    nikov
    1.52
    isecond
    1.49
    wise
    1.48
     bills
    1.48
    aments
    1.47
    table
    1.46
    burn
    1.45
    Activations Density 0.029%

    No Known Activations