© 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. 11548
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "ubiquity" and its variations

    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
    9
    +0.14
    0.8%
    213
    +0.12
    0.7%
    160
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    213
    +0.14
    0.03
    410
    +0.12
    0.03
    9
    +0.11
    0.02
    Negative Logits
    fully
    -2.04
     same
    -1.78
     direction
    -1.64
    ESULT
    -1.62
     Getty
    -1.58
     directions
    -1.44
     deaf
    -1.43
     await
    -1.40
     Forward
    -1.36
     msgid
    -1.35
    POSITIVE LOGITS
    erculosis
    2.66
    ercul
    2.29
    izarre
    2.23
    ilant
    2.22
    acteria
    2.21
    bing
    2.15
    oard
    2.14
    bles
    2.13
    ility
    2.05
    bies
    2.05
    Activations Density 0.155%

    No Known Activations