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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 12029
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "text" and related variations

    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
    +0.21
    1.2%
    77
    +0.17
    1.0%
    502
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    77
    +0.21
    0.02
    334
    +0.17
    0.03
    504
    +0.12
    0.02
    Negative Logits
    ĥ
    -2.35
     faith
    -1.99
    ↵		   
    -1.77
    ↵                                                                                                
    -1.77
    <|outofrange|>
    -1.77
    ↵↵                 
    -1.77
       ↵
    -1.77
                                                                          
    -1.77
    ↵       
    -1.77
    ↵                                      
    -1.77
    POSITIVE LOGITS
    ured
    2.15
    brush
    1.90
    block
    1.82
    box
    1.73
    area
    1.73
    strings
    1.73
    urized
    1.71
    books
    1.67
    book
    1.62
    board
    1.60
    Activations Density 0.118%

    No Known Activations