© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 4-RES-SM
    6. 14907
    Prev
    Next
    INDEX
    Explanations

    phrases related to completing or finalizing processes or actions.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @mwhanna

    key terms related to legislative processes and updates

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    21
    +0.28
    1.6%
    278
    +0.11
    0.6%
    133
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    234
    +0.28
    0.13
    15
    +0.11
    0.17
    133
    +0.10
    0.13
    Negative Logits
         ↵ 
    -7.51
                                                         
    -7.51
    ↵↵    
    -7.51
                                   
    -7.51
     ↵   
    -7.51
                                                                 
    -7.51
    ↵                               
    -7.51
    č↵č↵       
    -7.51
                                                                                                                                    
    -7.51
                                            
    -7.51
    POSITIVE LOGITS
     we
    2.48
     there
    2.19
     they
    2.07
     it
    1.89
     you
    1.83
     however
    1.79
     she
    1.56
     he
    1.54
    ingle
    1.41
    ucid
    1.38
    Activations Density 3.029%

    No Known Activations