© 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. 12430
    Prev
    Next
    INDEX
    Explanations

    references to the current date

    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
    56
    +0.12
    0.6%
    434
    +0.11
    0.6%
    498
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    163
    +0.12
    0.02
    458
    +0.11
    0.03
    389
    +0.11
    0.03
    Negative Logits
    ·¸
    -4.20
    ĻĤ
    -4.06
    ŀ
    -3.90
    Ļª
    -3.73
    Ĵ
    -3.68
    ĨĴ
    -3.63
    İ
    -3.62
     ↵           
    -3.57
    ↵                  
    -3.57
                ↵ 
    -3.57
    POSITIVE LOGITS
    abouts
    1.89
    dream
    1.84
    adays
    1.66
    ward
    1.63
    after
    1.52
    however
    1.50
    mare
    1.50
    tic
    1.50
    opan
    1.50
     announced
    1.50
    Activations Density 0.148%

    No Known Activations