© 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. 4-RES-SM
    11. 9114
    Prev
    Next
    INDEX
    Explanations

    references to work and employment statistics

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    70
    +0.13
    0.7%
    251
    +0.13
    0.7%
    318
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    318
    +0.13
    0.05
    70
    +0.13
    0.07
    159
    +0.12
    0.05
    Negative Logits
    ¡
    -3.83
    ľĵ
    -3.62
    ¿½
    -3.42
    Ĺ
    -3.39
    Ģ
    -3.38
    «
    -3.33
    ķ
    -3.27
    ĸ
    -3.20
    ĻĤ
    -3.19
    <|outofrange|>
    -3.19
    POSITIVE LOGITS
     Work
    3.38
     work
    3.17
    Work
    3.11
    work
    2.97
     WORK
    2.94
    working
    2.79
     working
    2.74
    worked
    2.73
     workspace
    2.65
     Working
    2.64
    Activations Density 1.102%

    No Known Activations