© 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. 2-RES-SM
    11. 28335
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to betting and gambling 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
    +0.14
    0.8%
    302
    +0.12
    0.7%
    295
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.14
    0.03
    38
    +0.12
    0.02
    174
    +0.11
    0.04
    Negative Logits
    ij
    -3.36
    Ŀ
    -3.22
    ·
    -3.20
    ĸ´
    -3.19
    °
    -3.06
    ³
    -3.05
    ĵ
    -3.03
    ¡
    -2.96
    Ļ
    -2.96
    Ł
    -2.90
    POSITIVE LOGITS
     lottery
    2.25
    chers
    1.89
    amethasone
    1.86
    makers
    1.84
     prizes
    1.83
    innings
    1.82
     winner
    1.74
    gins
    1.71
    gle
    1.67
    icipants
    1.67
    Activations Density 0.662%

    No Known Activations