© 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. 30004
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and calculations

    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
    448
    +0.14
    0.8%
    310
    +0.12
    0.6%
    207
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    251
    +0.14
    0.01
    391
    +0.12
    0.01
    359
    +0.11
    0.01
    Negative Logits
     alerted
    -1.66
    optera
    -1.47
     detection
    -1.37
     embol
    -1.36
    				
    -1.36
     @
    -1.35
     {}
    -1.34
     monitors
    -1.33
     disclosed
    -1.27
    ugin
    -1.27
    POSITIVE LOGITS
    ĨĴ
    2.23
    ¿
    1.96
    IJ
    1.93
    Ĵ
    1.85
    µ
    1.78
    ¥
    1.72
    Ŀ
    1.71
    Ļª
    1.67
    ¦
    1.61
    °
    1.59
    Activations Density 0.030%

    No Known Activations