Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27325
    Prev
    Next
    INDEX
    Explanations

    the command "ignore" in various contexts, indicating a focus on disregarding or bypassing certain information or messages

    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
    354
    +0.13
    0.7%
    369
    +0.12
    0.7%
    281
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.13
    0.04
    59
    +0.12
    0.03
    332
    +0.12
    0.03
    Negative Logits
     footsteps
    -1.93
    ¿½
    -1.91
    izes
    -1.79
    č↵  
    -1.78
    ↵        ↵       
    -1.78
    <|outofrange|>
    -1.78
    <|outofrange|>
    -1.78
    ↵↵   
    -1.78
      ↵ 
    -1.78
    <|padding|>
    -1.78
    POSITIVE LOGITS
    \.
    1.87
    uer
    1.81
    \)
    1.80
    ULT
    1.62
     downloaded
    1.58
    uet
    1.58
    cke
    1.56
    uber
    1.50
    reland
    1.50
    ienn
    1.48
    Activations Density 0.061%

    No Known Activations