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. 11773
    Prev
    Next
    INDEX
    Explanations

    keywords related to the concept of quantity or numerical values

    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
    +0.53
    3.8%
    111
    +0.41
    3.0%
    419
    +0.09
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.53
    0.20
    156
    +0.41
    0.18
    71
    +0.09
    0.17
    Negative Logits
    ¿½
    -2.51
    ↵                                                 
    -2.11
     ↵    
    -2.11
    ↵↵         
    -2.11
    ↵                                          
    -2.11
                                                                  
    -2.11
    ↵↵                                         
    -2.11
    <|outofrange|>
    -2.11
    ↵                                         
    -2.11
    ↵↵           
    -2.11
    POSITIVE LOGITS
    anks
    1.61
    agra
    1.35
    uclear
    1.34
    ovascular
    1.26
    ginx
    1.26
    ucle
    1.21
    ank
    1.20
    roscopic
    1.20
    atics
    1.18
     branches
    1.18
    Activations Density 0.147%

    No Known Activations