© 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 EvalsExportsAPI 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. 12448
    Prev
    Next
    INDEX
    Explanations

    regulatory terms and concepts related to governance or oversight

    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
    203
    +0.13
    0.7%
    443
    +0.12
    0.7%
    412
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    443
    +0.13
    0.03
    386
    +0.12
    0.01
    203
    +0.11
    0.02
    Negative Logits
    llo
    -1.68
    lla
    -1.61
    manship
    -1.58
    lli
    -1.54
     opposite
    -1.51
    ware
    -1.49
    board
    -1.47
     justice
    -1.47
     myself
    -1.46
    brew
    -1.41
    POSITIVE LOGITS
    istered
    3.36
    eneration
    2.47
    isters
    2.35
    gae
    2.26
    ression
    2.23
    ional
    2.16
    imental
    2.15
    ulations
    2.13
    iments
    2.08
    ions
    2.05
    Activations Density 0.130%

    No Known Activations