© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 11943
    Prev
    Next
    INDEX
    Explanations

    instances of the word "better."

    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
    392
    +0.14
    0.8%
    341
    +0.13
    0.7%
    225
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.14
    0.03
    231
    +0.13
    0.03
    149
    +0.12
    0.04
    Negative Logits
    iasis
    -1.69
    unnumbered
    -1.66
    ystems
    -1.50
    ĵ
    -1.48
    ycle
    -1.47
    ycler
    -1.44
    TRODUCTION
    -1.38
    ycl
    -1.36
    ·
    -1.36
    £
    -1.34
    POSITIVE LOGITS
     than
    3.70
    than
    2.75
    Than
    2.71
     suited
    2.62
     Than
    2.34
     behaved
    2.26
     known
    1.93
     equipped
    1.92
     acquainted
    1.83
    ment
    1.79
    Activations Density 0.189%

    No Known Activations