© 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. Residuals
    5. 2-RES-SM
    6. 11158
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    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
    459
    +0.18
    1.0%
    320
    +0.14
    0.8%
    392
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    459
    +0.18
    0.03
    359
    +0.14
    0.02
    125
    +0.13
    0.02
    Negative Logits
    č↵           
    -3.92
    č↵       
    -3.91
    ↵         
    -3.91
    ↵                                                   
    -3.91
                                     
    -3.91
      ↵   
    -3.91
    <|outofrange|>
    -3.91
              ↵ 
    -3.91
                                                                              
    -3.91
                                                                                                                                                                                                                                    
    -3.91
    POSITIVE LOGITS
     petition
    1.50
     petitions
    1.43
    blast
    1.43
    thems
    1.41
    Supporting
    1.36
    ze
    1.32
    iday
    1.32
    ([]
    1.31
    ussions
    1.30
     outbreak
    1.29
    Activations Density 0.032%

    No Known Activations