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. 26785
    Prev
    Next
    INDEX
    Explanations

    terms related to code or programming 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/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
    253
    +0.14
    0.8%
    133
    +0.12
    0.7%
    92
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    183
    +0.14
    0.00
    390
    +0.12
    0.00
    471
    +0.12
    0.00
    Negative Logits
    king
    -1.79
    forth
    -1.67
    leton
    -1.66
    hof
    -1.58
    ½
    -1.57
    ¹
    -1.54
    Ŀ
    -1.51
    ↵    ↵   
    -1.51
              
    -1.51
    ↵                 
    -1.51
    POSITIVE LOGITS
    .'"
    1.55
    .-
    1.50
    htra
    1.47
     _________________________________
    1.41
     where
    1.40
     ÂĹ
    1.40
    .''
    1.39
    ,'"
    1.39
    '"
    1.35
     colors
    1.32
    Activations Density 0.000%

    No Known Activations