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. Residuals
    5. 2-RES-SM
    6. 29549
    Prev
    Next
    INDEX
    Explanations

    Java programming constructs and related libraries

    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
    +0.24
    1.4%
    181
    +0.13
    0.7%
    93
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    181
    +0.24
    0.06
    250
    +0.13
    0.05
    80
    +0.12
    0.04
    Negative Logits
    its
    -1.73
     successfully
    -1.60
     reproduced
    -1.53
     reproduce
    -1.53
     ]
    -1.51
    denly
    -1.50
    cludes
    -1.48
      ↵
    -1.45
    ccess
    -1.42
     regards
    -1.41
    POSITIVE LOGITS
    Ļª
    3.29
    ĨĴ
    3.19
    ĭ
    3.14
    ↵                
    3.13
                       
    3.13
    <|outofrange|>
    3.13
    č↵        
    3.13
                                                                            
    3.13
                                             
    3.13
    <|outofrange|>
    3.13
    Activations Density 0.307%

    No Known Activations