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. Residuals
    5. 2-RES-SM
    6. 29472
    Prev
    Next
    INDEX
    Explanations

    fragments of code or programming language syntax

    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
    47
    +0.16
    0.9%
    153
    +0.15
    0.9%
    441
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    441
    +0.16
    -0.00
    135
    +0.15
    0.13
    47
    +0.14
    0.16
    Negative Logits
    erville
    -1.55
     Brewing
    -1.50
     Panama
    -1.47
     Venezuela
    -1.39
    ÂĴ
    -1.38
     Kubernetes
    -1.37
     Agriculture
    -1.37
     agriculture
    -1.36
     Excell
    -1.34
     Plants
    -1.31
    POSITIVE LOGITS
    ↵↵    
    2.17
    ↵                        
    2.17
                                                                                   
    2.17
    ↵                       
    2.17
                      
    2.17
    <|outofrange|>
    2.17
    ↵                          
    2.17
                                           
    2.17
                                                                               
    2.17
           ↵ 
    2.17
    Activations Density 5.125%

    No Known Activations