© 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. 1-RES-SM
    11. 26594
    Prev
    Next
    INDEX
    Explanations

    mentions of lifestyle and its variations

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    +0.20
    1.2%
    214
    +0.11
    0.7%
    298
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    309
    +0.20
    0.02
    38
    +0.11
    0.01
    298
    +0.11
    0.01
    Negative Logits
    ķ
    -2.24
    º
    -2.16
    -2.03
              ↵
    -2.03
    ↵↵↵
    -2.03
    ↵
    -2.03
    -2.03
    <|outofrange|>
    -2.03
    -2.03
    -2.03
    POSITIVE LOGITS
     preferences
    1.72
     variables
    1.70
    ISM
    1.59
     traits
    1.55
    atics
    1.51
    WISE
    1.51
    Variables
    1.49
     adaptation
    1.45
    finder
    1.43
     behaviours
    1.43
    Activations Density 0.128%

    No Known Activations