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. 27259
    Prev
    Next
    INDEX
    Explanations

    phrases related to cooking instructions or ingredients

    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
    334
    +0.12
    0.7%
    246
    +0.11
    0.6%
    252
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.12
    0.47
    98
    +0.11
    0.22
    23
    +0.11
    0.37
    Negative Logits
    ↵↵                   
    -3.18
    <|outofrange|>
    -3.18
    č↵                   
    -3.18
                                               
    -3.18
    ↵           
    -3.18
    ↵↵         
    -3.18
                             
    -3.18
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    
    -3.18
                                                                                  
    -3.18
                                                                                   
    -3.18
    POSITIVE LOGITS
    iji
    1.55
    ~/
    1.55
    ICT
    1.53
    interacting
    1.47
    ariant
    1.47
    night
    1.45
    gently
    1.42
    getting
    1.42
    upon
    1.41
    latest
    1.40
    Activations Density 6.448%

    No Known Activations