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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 11668
    Prev
    Next
    INDEX
    Explanations

    commands related to inserting data

    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
    +0.21
    1.2%
    430
    +0.13
    0.7%
    344
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.21
    0.01
    344
    +0.13
    0.02
    376
    +0.12
    0.00
    Negative Logits
    Ī
    -2.47
    Ĥ¬
    -2.04
                                            
    -1.97
    ↵↵↵      
    -1.97
                                                    
    -1.97
    č↵č↵           
    -1.97
              ↵ 
    -1.97
    ↵  ³³³
    -1.97
    č↵        
    -1.97
    ↵    ↵   
    -1.97
    POSITIVE LOGITS
    itive
    1.60
     controls
    1.58
    ions
    1.56
    IONS
    1.53
     into
    1.52
    ionate
    1.52
     INTO
    1.51
    jections
    1.46
    able
    1.46
    ible
    1.46
    Activations Density 0.096%

    No Known Activations