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. 29562
    Prev
    Next
    INDEX
    Explanations

    terms related to germs and their associated biological concepts

    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
    74
    +0.14
    0.8%
    431
    +0.13
    0.7%
    77
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.14
    0.02
    74
    +0.13
    0.02
    431
    +0.13
    0.02
    Negative Logits
    Ļª
    -2.67
                                                                                                                                                                                                                                                                    
    -2.64
    ↵                                 
    -2.64
    ↵                             
    -2.64
    ↵↵                   
    -2.64
              ↵ 
    -2.64
     ↵       
    -2.64
    <|outofrange|>
    -2.64
    ↵             
    -2.64
                                              
    -2.64
    POSITIVE LOGITS
    osities
    1.93
    osity
    1.88
    ously
    1.84
    ulence
    1.80
    andom
    1.79
    arium
    1.74
    ophage
    1.69
    acy
    1.53
     unfolded
    1.48
    aceut
    1.43
    Activations Density 0.245%

    No Known Activations