Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12181
    Prev
    Next
    INDEX
    Explanations

    data structures and formatting elements commonly used in programming languages

    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
    161
    +0.13
    0.8%
    247
    +0.13
    0.7%
    74
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.13
    0.05
    161
    +0.13
    0.04
    47
    +0.12
    0.10
    Negative Logits
    ĻĤ
    -3.51
    ±
    -2.84
    ¿½
    -2.62
      ↵ 
    -2.58
                         
    -2.58
    č↵    
    -2.58
            ↵ 
    -2.58
                                                  
    -2.58
     ↵      
    -2.58
                                                           
    -2.58
    POSITIVE LOGITS
    $^{-
    1.79
    ArgumentException
    1.58
     GHz
    1.57
    Hz
    1.52
     integer
    1.50
    ensity
    1.48
    GHz
    1.47
     dB
    1.47
    olerance
    1.42
     brightness
    1.41
    Activations Density 1.726%

    No Known Activations