© 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. 1-RES-SM
    11. 24750
    Prev
    Next
    INDEX
    Explanations

    variations of the word "option."

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    68
    +0.11
    0.6%
    358
    +0.11
    0.6%
    376
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    358
    +0.11
    0.01
    427
    +0.11
    0.01
    215
    +0.11
    0.01
    Negative Logits
    Ļª
    -3.90
    ĻĤ
    -3.81
    »¿
    -3.68
    ¿
    -3.54
    ĨĴ
    -3.53
    ĩ
    -3.49
    ®
    -3.44
    Į
    -3.38
    §
    -3.37
    Ĵ
    -3.37
    POSITIVE LOGITS
    ftware
    1.75
    inux
    1.73
    nement
    1.64
    mozilla
    1.60
     precluded
    1.56
     protected
    1.53
    holder
    1.46
     administrator
    1.45
     preserved
    1.43
     continued
    1.41
    Activations Density 0.048%

    No Known Activations