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. 11584
    Prev
    Next
    INDEX
    Explanations

    references to Jesus Christ and related religious themes

    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
    91
    +0.16
    0.9%
    177
    +0.13
    0.7%
    410
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.16
    0.04
    385
    +0.13
    0.02
    177
    +0.12
    0.03
    Negative Logits
    ↵↵                                         
    -2.49
    ↵                                                                                                
    -2.49
    ↵↵↵       
    -2.49
    ↵↵                                             
    -2.49
               
    -2.49
    ↵                                                
    -2.49
    <|outofrange|>
    -2.49
    č↵       
    -2.49
    ↵↵                                
    -2.49
    č↵  
    -2.49
    POSITIVE LOGITS
    church
    1.83
    ensen
    1.77
    ophers
    1.72
     signs
    1.65
     Christ
    1.63
    ophe
    1.59
     Ages
    1.58
     Himself
    1.55
    opher
    1.52
    ian
    1.52
    Activations Density 0.287%

    No Known Activations