© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 15139
    Prev
    Next
    INDEX
    Explanations

    references to inventions or innovative ideas

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    21
    +0.19
    1.1%
    3
    +0.14
    0.8%
    216
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    3
    +0.19
    0.01
    216
    +0.14
    0.01
    399
    +0.12
    0.00
    Negative Logits
     (@
    -1.76
     |
    -1.54
     /
    -1.51
     [`
    -1.49
     ["
    -1.47
    >/
    -1.46
    etine
    -1.44
    =%
    -1.43
     ^
    -1.41
     https
    -1.39
    POSITIVE LOGITS
     embodiments
    1.75
    abstract
    1.75
     further
    1.73
    further
    1.61
     invention
    1.61
     FIG
    1.57
    METHOD
    1.51
     sectional
    1.49
    Accordingly
    1.47
     FIGS
    1.46
    Activations Density 0.029%

    No Known Activations