© 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. 1-RES-SM
    11. 29516
    Prev
    Next
    INDEX
    Explanations

    mentions of banks and banking-related terms

    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
    +0.16
    0.9%
    295
    +0.14
    0.8%
    357
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    295
    +0.16
    0.02
    357
    +0.14
    0.02
    45
    +0.10
    0.02
    Negative Logits
     gender
    -1.77
     whole
    -1.62
     vaginal
    -1.58
     bipartisan
    -1.51
     prenatal
    -1.50
    AMPLE
    -1.49
     drastic
    -1.48
     genital
    -1.46
     constant
    -1.46
     placenta
    -1.43
    POSITIVE LOGITS
    notes
    2.46
    yard
    2.20
    ruptcy
    1.99
    erra
    1.97
    esian
    1.85
    sters
    1.84
    etica
    1.83
    yards
    1.82
    edly
    1.79
    ed
    1.79
    Activations Density 0.094%

    No Known Activations