© 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. MLP Post
    5. 2-MLP-SM
    6. 25964
    Prev
    Next
    INDEX
    Explanations

    references to specific medical devices or techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/2-mlp-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_mlp_out
    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
    +0.23
    1.3%
    23
    +0.15
    0.8%
    303
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    303
    +0.23
    0.03
    511
    +0.15
    0.02
    8
    +0.12
    0.03
    Negative Logits
    Īĺ
    -2.48
    ↵    
    -2.46
    ↵               
    -2.46
    ↵↵            
    -2.46
             
    -2.46
     ↵         
    -2.46
    č↵       
    -2.46
    ↵        
    -2.46
    č↵                       
    -2.46
                  ↵ 
    -2.46
    POSITIVE LOGITS
     curve
    1.57
    utes
    1.46
     plague
    1.33
     Cur
    1.31
    rophic
    1.30
     Republic
    1.25
    require
    1.25
    atts
    1.24
     monolayer
    1.24
     Progress
    1.22
    Activations Density 0.330%

    No Known Activations