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. 1-RES-SM
    6. 26792
    Prev
    Next
    INDEX
    Explanations

    bracketed elements in code or structured formats

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    478
    +0.20
    1.1%
    29
    +0.11
    0.6%
    28
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    51
    +0.20
    0.04
    318
    +0.11
    0.05
    354
    +0.11
    0.04
    Negative Logits
    uate
    -1.62
    uated
    -1.50
    uates
    -1.50
    insky
    -1.49
    asek
    -1.43
    ually
    -1.42
    uating
    -1.38
     thereon
    -1.33
    atto
    -1.32
     residue
    -1.28
    POSITIVE LOGITS
    į
    2.43
    ľ
    2.12
     ↵   
    2.08
    ↵    ↵   
    2.08
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    
    2.08
    <|outofrange|>
    2.08
                      
    2.08
    <|outofrange|>
    2.08
                                            
    2.08
                                                                                   
    2.08
    Activations Density 0.247%

    No Known Activations