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. 0-MLP-SM
    6. 27538
    Prev
    Next
    INDEX
    Explanations

    affirmative statements indicating certainty

    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
    148
    +0.12
    0.7%
    300
    +0.12
    0.6%
    218
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.12
    0.04
    218
    +0.12
    0.05
    300
    +0.12
    0.05
    Negative Logits
     class
    -1.57
     altogether
    -1.50
     always
    -1.49
     previously
    -1.48
     responded
    -1.42
     outright
    -1.41
     long
    -1.40
     answered
    -1.40
     ever
    -1.38
     explained
    -1.37
    POSITIVE LOGITS
    »¿
    2.93
    ķ
    2.72
    ¿
    2.68
    ¸
    2.62
    Ļ
    2.58
    ↵                                  
    2.55
    ↵                                                                                                                                                                                                                                                                
    2.55
                         
    2.55
    ↵                    
    2.55
    ↵       
    2.55
    Activations Density 0.040%

    No Known Activations