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. 26745
    Prev
    Next
    INDEX
    Explanations

    references to measurement and evaluation in various contexts

    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
    156
    +0.19
    1.1%
    352
    +0.14
    0.8%
    498
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    498
    +0.19
    0.03
    352
    +0.14
    0.03
    454
    +0.12
    0.02
    Negative Logits
    ¬
    -1.92
    »
    -1.83
    ¸
    -1.74
    ±
    -1.72
    Ł
    -1.70
    ¯
    -1.68
    ↵↵                               
    -1.54
    ↵                                     
    -1.54
    č↵           
    -1.54
                                       
    -1.54
    POSITIVE LOGITS
    imeter
    1.64
    imeters
    1.61
     purposes
    1.56
    imet
    1.56
     accuracy
    1.55
     weight
    1.52
    eters
    1.52
     units
    1.52
    etically
    1.51
    makers
    1.50
    Activations Density 0.097%

    No Known Activations