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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 11097
    Prev
    Next
    INDEX
    Explanations

    structured data elements, particularly curly braces

    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
    478
    +0.20
    1.1%
    100
    +0.14
    0.8%
    290
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    51
    +0.20
    0.04
    100
    +0.14
    0.04
    38
    +0.13
    0.03
    Negative Logits
    ĻĤ
    -2.69
    »¿
    -2.57
    Ł
    -2.39
                             
    -2.38
                                                                                 
    -2.38
    ↵                          
    -2.38
    ↵↵                   
    -2.38
                                                                                                                                                                                                                                                                    
    -2.38
                                              
    -2.38
                                                                                   
    -2.38
    POSITIVE LOGITS
    fileID
    2.01
    amsfonts
    1.70
    mium
    1.53
    unnumbered
    1.53
    +}
    1.50
    wasysym
    1.45
    amssymb
    1.44
     candid
    1.41
     neut
    1.37
    mathrsfs
    1.36
    Activations Density 0.124%

    No Known Activations