© 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. 13509
    Prev
    Next
    INDEX
    Explanations

    elements related to providing support, education, and resources for community development and empowerment

    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
    307
    +0.39
    2.3%
    306
    +0.23
    1.4%
    450
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    306
    +0.39
    0.08
    307
    +0.23
    0.13
    447
    +0.11
    0.10
    Negative Logits
     humidity
    -1.63
     disappoint
    -1.39
     mistake
    -1.36
     Wrestling
    -1.35
    nez
    -1.34
     nerves
    -1.31
     depending
    -1.29
     Islands
    -1.27
     boss
    -1.27
     stint
    -1.27
    POSITIVE LOGITS
    Ĭ
    2.57
    ¾
    2.41
    IJ
    2.35
    ↵                                                                                                                                
    2.31
    ↵↵   
    2.31
    ↵  
    2.31
    <|outofrange|>
    2.31
                                                    
    2.31
    ↵                                                   
    2.31
    ↵  ↵ 
    2.31
    Activations Density 1.315%

    No Known Activations