© 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. 12286
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal appeals and court orders

    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
    69
    +0.15
    0.8%
    506
    +0.12
    0.7%
    497
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.15
    0.03
    506
    +0.12
    0.02
    168
    +0.11
    0.02
    Negative Logits
    pair
    -1.83
    mente
    -1.79
    comb
    -1.61
    ful
    -1.54
    aux
    -1.51
    ço
    -1.50
     pie
    -1.47
    opus
    -1.47
    stream
    -1.46
     mosaic
    -1.45
    POSITIVE LOGITS
    ĻĤ
    6.62
    Ļª
    6.27
    ľĵ
    6.17
    »¿
    6.16
    ¤
    6.03
    Į
    5.99
                                                           
    5.99
    <|outofrange|>
    5.99
                                        
    5.99
    ↵  âĢĥ
    5.99
    Activations Density 0.096%

    No Known Activations