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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 12597
    Prev
    Next
    INDEX
    Explanations

    references to Google and its associated services or tools

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    138
    +0.15
    0.8%
    307
    +0.14
    0.8%
    148
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.11
    156
    +0.14
    0.10
    510
    +0.12
    0.09
    Negative Logits
    Ļª
    -2.72
    Į
    -2.30
    £
    -2.21
    ŀ
    -2.03
    ĻĤ
    -2.02
    Īĺ
    -2.00
    ¿½
    -1.98
    º
    -1.95
    ĨĴ
    -1.93
     Willie
    -1.89
    POSITIVE LOGITS
     Google
    4.51
    Google
    4.21
     google
    3.74
    google
    3.68
     GOOGLE
    3.63
     Chrome
    3.06
    googleapis
    3.04
    goog
    2.88
     Android
    2.64
     Pixel
    2.61
    Activations Density 0.811%

    No Known Activations