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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27466
    Prev
    Next
    INDEX
    Explanations

    the word "is" used 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__mlp-sm_processed/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    23
    +0.40
    2.4%
    478
    +0.17
    1.0%
    337
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    337
    +0.40
    0.24
    17
    +0.17
    0.16
    233
    +0.15
    0.17
    Negative Logits
    č↵             
    -4.02
    ↵               
    -4.02
    ↵↵    
    -4.02
                                                                                                                                    
    -4.02
    ↵			   
    -4.02
    ↵↵        
    -4.02
    č↵           
    -4.02
                                                        
    -4.02
                                                                    
    -4.02
    <|outofrange|>
    -4.02
    POSITIVE LOGITS
    rael
    1.89
     expected
    1.82
    opropyl
    1.81
     increasing
    1.71
     indicated
    1.68
     decreasing
    1.67
    omerase
    1.64
     caspase
    1.62
     unfair
    1.61
    ocrates
    1.59
    Activations Density 6.977%

    No Known Activations