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. 29395
    Prev
    Next
    INDEX
    Explanations

    specific programming syntax and structure, particularly related to object initialization and method definitions in code

    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
    394
    +0.13
    0.7%
    338
    +0.11
    0.6%
    380
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    79
    +0.13
    0.03
    131
    +0.11
    0.03
    84
    +0.11
    0.03
    Negative Logits
    orer
    -1.69
    liness
    -1.64
    lessness
    -1.61
    )\].
    -1.56
    .).
    -1.53
    :**
    -1.52
    odend
    -1.50
    .);
    -1.49
    vier
    -1.48
    .](
    -1.47
    POSITIVE LOGITS
    ij
    4.13
    Ĵ
    4.13
    ĵ
    4.08
    ↵                                                
    4.00
    ↵↵                           
    4.00
    <|outofrange|>
    4.00
    č↵                       
    4.00
    ↵↵↵   
    4.00
    ↵      
    4.00
    ↵    ↵   
    4.00
    Activations Density 0.294%

    No Known Activations