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. 11746
    Prev
    Next
    INDEX
    Explanations

    references to refugee situations and humanitarian crises

    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
    156
    +0.32
    2.0%
    186
    +0.31
    2.0%
    56
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.32
    0.12
    56
    +0.31
    -0.00
    210
    +0.17
    0.03
    Negative Logits
    ↵                                                                
    -4.97
    č↵                   
    -4.97
              ↵ 
    -4.97
    ↵                               
    -4.97
                                           
    -4.97
    ↵↵           
    -4.97
    ↵                          
    -4.97
                                                                                                                                                                                                                                                                    
    -4.97
                    
    -4.97
    <|outofrange|>
    -4.97
    POSITIVE LOGITS
     fleeing
    2.58
     injured
    2.07
     flee
    1.98
     displaced
    1.86
     unemployed
    1.83
     emig
    1.81
     occupying
    1.79
     stric
    1.78
     illegally
    1.77
     seized
    1.77
    Activations Density 2.265%

    No Known Activations