© 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. 11104
    Prev
    Next
    INDEX
    Explanations

    references to stress and its related factors

    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
    +0.23
    1.3%
    356
    +0.12
    0.7%
    311
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    311
    +0.23
    0.02
    115
    +0.12
    0.02
    361
    +0.12
    0.02
    Negative Logits
    leans
    -1.85
    sembles
    -1.73
     parte
    -1.63
     sworn
    -1.62
     vez
    -1.56
     search
    -1.51
    ubicin
    -1.50
    ieur
    -1.49
    ffield
    -1.49
    TRODUCTION
    -1.48
    POSITIVE LOGITS
     tolerance
    2.13
    iness
    2.12
     occasion
    2.03
    ier
    2.01
     onset
    1.99
     conditions
    1.91
    ingly
    1.86
     levels
    1.83
    eer
    1.81
    stress
    1.80
    Activations Density 0.136%

    No Known Activations