© 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. 29424
    Prev
    Next
    INDEX
    Explanations

    the repeated use of the word "know."

    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
    246
    +0.14
    0.8%
    497
    +0.13
    0.7%
    72
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    246
    +0.14
    0.04
    72
    +0.13
    0.04
    113
    +0.12
    0.03
    Negative Logits
    ij
    -2.30
    ½
    -2.15
    Ģ
    -2.08
    ĵ
    -2.04
    ĸ
    -2.02
    ·¸
    -1.97
    Ĵ
    -1.94
    Ķ
    -1.94
    ĨĴ
    -1.89
    Ļª
    -1.86
    POSITIVE LOGITS
    ingly
    2.19
     how
    1.78
     whats
    1.74
     what
    1.72
    what
    1.71
    how
    1.67
     thanks
    1.57
     something
    1.55
     valuable
    1.54
     sorts
    1.54
    Activations Density 0.132%

    No Known Activations