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. MLP Post
    5. 2-MLP-SM
    6. 26271
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "odd."

    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%
    198
    +0.14
    0.8%
    351
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    360
    +0.23
    0.01
    275
    +0.14
    0.00
    23
    +0.12
    0.02
    Negative Logits
    :`
    -1.84
    $/
    -1.70
    ÃŃa
    -1.70
    /-
    -1.67
    ~:
    -1.53
     /**
    -1.51
     Telescope
    -1.50
    iom
    -1.47
    itat
    -1.47
    #{$
    -1.46
    POSITIVE LOGITS
    Ł
    2.22
    ±
    2.19
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    2.12
    č↵             
    2.10
    ↵↵                       
    2.10
                                                                        
    2.10
                                                                                                                                                                                                                                                                    
    2.10
    ↵                                                  
    2.10
                             
    2.10
    ↵            
    2.10
    Activations Density 0.313%

    No Known Activations