© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 26906
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to."

    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
    358
    +0.14
    0.8%
    263
    +0.12
    0.7%
    78
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    358
    +0.14
    0.06
    500
    +0.12
    0.05
    435
    +0.12
    0.04
    Negative Logits
    ĸ
    -2.44
    Ĭ
    -2.23
    ĸ´
    -2.21
    ĩ
    -2.10
    ļ
    -2.07
    Ĩ
    -2.05
    ¡
    -1.85
    ¨
    -1.84
    Ĺ
    -1.80
    Ģ
    -1.80
    POSITIVE LOGITS
     handle
    2.08
     reproduce
    1.88
     detect
    1.79
     safely
    1.76
     successfully
    1.74
     save
    1.74
     capture
    1.74
     cope
    1.68
     retrieve
    1.66
     resist
    1.61
    Activations Density 0.212%

    No Known Activations