© 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. 30707
    Prev
    Next
    INDEX
    Explanations

    verbs related to gaming or play activities

    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
    323
    +0.14
    0.8%
    156
    +0.14
    0.8%
    484
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    323
    +0.14
    0.03
    484
    +0.14
    0.04
    53
    +0.14
    0.04
    Negative Logits
    ·
    -1.73
    ){#
    -1.67
    µ
    -1.64
     rise
    -1.60
    $$\
    -1.58
     occ
    -1.56
    ampsia
    -1.55
     descent
    -1.52
    \|_{\
    -1.50
     vanishing
    -1.48
    POSITIVE LOGITS
    grounds
    2.16
     games
    2.13
    mates
    2.00
    boys
    1.94
    boy
    1.87
    nament
    1.81
    abouts
    1.78
    guns
    1.72
     sports
    1.71
     game
    1.70
    Activations Density 0.155%

    No Known Activations