© 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. 10187
    Prev
    Next
    INDEX
    Explanations

    words associated with work and productivity

    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
    364
    +0.15
    0.8%
    337
    +0.12
    0.7%
    184
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    364
    +0.15
    0.05
    184
    +0.12
    0.05
    74
    +0.11
    0.03
    Negative Logits
    illion
    -1.84
    apine
    -1.74
    gent
    -1.56
    gian
    -1.44
    Ibid
    -1.43
    irie
    -1.42
    edia
    -1.40
    ze
    -1.39
     disbelief
    -1.37
    anean
    -1.37
    POSITIVE LOGITS
    manship
    3.61
    Ķ
    3.29
    bench
    3.07
    ¹
    2.95
    station
    2.94
    places
    2.93
    £
    2.89
    aday
    2.88
     ethic
    2.88
    horse
    2.85
    Activations Density 0.341%

    No Known Activations