© 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. 9285
    Prev
    Next
    INDEX
    Explanations

    terms related to consumer protection and regulatory agencies

    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
    21
    +0.18
    1.0%
    78
    +0.16
    0.9%
    126
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    98
    +0.18
    0.04
    11
    +0.16
    0.07
    418
    +0.13
    0.04
    Negative Logits
    ensively
    -1.69
    itively
    -1.69
    matically
    -1.65
    ically
    -1.55
    ally
    -1.52
    pieces
    -1.50
    ontally
    -1.48
    fully
    -1.47
    nos
    -1.47
    oki
    -1.46
    POSITIVE LOGITS
     Affairs
    2.66
     Policy
    2.58
     Economic
    2.54
     Fund
    2.44
     Protection
    2.38
     Industry
    2.36
     Committee
    2.35
     Management
    2.31
     Association
    2.30
     Intelligence
    2.29
    Activations Density 0.593%

    No Known Activations