© 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. 13899
    Prev
    Next
    INDEX
    Explanations

    references to financial concepts and implications within economic discussions

    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
    348
    +0.13
    0.7%
    25
    +0.12
    0.7%
    466
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    25
    +0.13
    0.17
    474
    +0.12
    0.13
    56
    +0.11
    0.05
    Negative Logits
    igraphy
    -1.68
    ViewById
    -1.56
    anguage
    -1.52
    datepicker
    -1.47
    idades
    -1.47
    blockList
    -1.46
    tron
    -1.45
    iens
    -1.40
    namese
    -1.38
    nor
    -1.36
    POSITIVE LOGITS
     death
    2.48
     deaths
    2.45
     fatal
    2.36
     damaging
    2.32
     demise
    2.29
     devastating
    2.13
     eventually
    2.12
     catastrophic
    2.10
     worse
    2.10
     suicide
    2.04
    Activations Density 3.463%

    No Known Activations