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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 29094
    Prev
    Next
    INDEX
    Explanations

    references to authors and author metadata in documents

    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
    407
    +0.13
    0.7%
    410
    +0.12
    0.6%
    443
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    163
    +0.13
    0.02
    410
    +0.12
    0.03
    174
    +0.11
    0.03
    Negative Logits
    Ł
    -1.49
    ↵       
    -1.49
    ↵  Âł
    -1.49
                                                         
    -1.49
    ↵                    
    -1.49
                         
    -1.49
                    
    -1.49
       ↵ 
    -1.49
                                                                                  
    -1.49
    ↵                            
    -1.49
    POSITIVE LOGITS
    itatively
    2.32
    ization
    2.31
    izations
    2.20
    ities
    2.15
    esses
    2.06
    izes
    2.05
    ised
    1.99
    iousness
    1.85
    itative
    1.84
    isation
    1.83
    Activations Density 0.163%

    No Known Activations