© 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. 10828
    Prev
    Next
    INDEX
    Explanations

    phrases related to user registration and website navigation instructions

    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
    139
    +0.13
    0.7%
    212
    +0.12
    0.7%
    56
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    260
    +0.13
    0.06
    19
    +0.12
    0.07
    263
    +0.12
    0.09
    Negative Logits
    ↵           
    -2.11
                                              
    -2.11
    č↵č↵           
    -2.11
    ↵                               
    -2.11
                             
    -2.11
    ↵                              
    -2.11
    <|outofrange|>
    -2.11
    ↵                             
    -2.11
                                                                                                                                                                                                                                                                    
    -2.11
    ↵↵                   
    -2.11
    POSITIVE LOGITS
     recommend
    2.07
     recommends
    1.85
     calendar
    1.62
     your
    1.61
     recommendation
    1.50
     season
    1.50
     recommended
    1.48
     count
    1.46
     acquaintance
    1.46
     instructions
    1.46
    Activations Density 1.699%

    No Known Activations