© 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. 29032
    Prev
    Next
    INDEX
    Explanations

    references to the concept of time and its passage

    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
    113
    +0.16
    0.9%
    269
    +0.10
    0.6%
    499
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    113
    +0.16
    0.06
    358
    +0.10
    0.05
    471
    +0.10
    0.04
    Negative Logits
    iquity
    -1.72
    Ŀ
    -1.67
     guilty
    -1.67
    áĢ¯
    -1.66
    +-+-
    -1.60
    ĥ
    -1.55
    ĻĤ
    -1.53
    others
    -1.52
    -1.51
    -1.51
    POSITIVE LOGITS
     ago
    1.80
     horizon
    1.71
     determining
    1.66
     chess
    1.64
    istical
    1.60
    ward
    1.60
     during
    1.60
    istically
    1.58
    ulates
    1.56
     radar
    1.56
    Activations Density 0.178%

    No Known Activations