© 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 EvalsExportsAPI 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. 30541
    Prev
    Next
    INDEX
    Explanations

    references to golf-related terms and 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
    156
    +0.15
    0.9%
    230
    +0.12
    0.7%
    456
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    173
    +0.15
    0.03
    230
    +0.12
    0.02
    128
    +0.12
    0.01
    Negative Logits
    onas
    -1.69
     responding
    -1.62
     cref
    -1.58
     discl
    -1.57
    igm
    -1.57
     matter
    -1.56
     contacting
    -1.47
     silence
    -1.45
    akin
    -1.44
     convincing
    -1.44
    POSITIVE LOGITS
     clubs
    2.08
     enthusiasts
    1.86
     Club
    1.78
    Players
    1.74
     season
    1.72
    Sports
    1.72
    Club
    1.70
     club
    1.69
    Olympic
    1.63
     tournaments
    1.61
    Activations Density 0.186%

    No Known Activations