© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 28554
    Prev
    Next
    INDEX
    Explanations

    references to nutrients, vitamins, and their health impacts

    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
    +0.22
    1.3%
    184
    +0.13
    0.8%
    176
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.22
    0.03
    32
    +0.13
    0.03
    321
    +0.11
    0.03
    Negative Logits
    ĥ½
    -4.09
    ↵↵            
    -4.00
    ↵  âĢĥ
    -4.00
    ↵               
    -4.00
    <|outofrange|>
    -4.00
    ↵	     
    -4.00
    ↵        
    -4.00
    <|outofrange|>
    -4.00
                   
    -4.00
    ↵    ↵   
    -4.00
    POSITIVE LOGITS
    mith
    2.31
    ystems
    2.17
    pace
    2.15
    hell
    2.13
    elves
    1.93
    PEC
    1.93
    creen
    1.92
    ource
    1.87
    ystem
    1.87
    apon
    1.85
    Activations Density 0.310%

    No Known Activations