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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12163
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    423
    +0.13
    0.7%
    500
    +0.11
    0.6%
    277
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    -0.13
    0.00
    1
    -0.11
    0.00
    2
    -0.11
    0.00
    Negative Logits
     rivals
    -1.62
    documentclass
    -1.58
     keyword
    -1.44
     genres
    -1.40
     deprecated
    -1.37
     lure
    -1.34
     erotic
    -1.32
     competitors
    -1.31
     accent
    -1.31
     Angl
    -1.31
    POSITIVE LOGITS
    ↵  
    3.98
    ↵                          
    3.98
    ↵↵                   
    3.98
    ↵                           
    3.98
    ↵                                           
    3.98
    ↵                                              
    3.98
                                                                    
    3.98
    ↵                                     
    3.98
    Â
    3.98
    ↵↵    
    3.98
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.