© 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. 8715
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific findings and research results

    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
    348
    +0.15
    0.9%
    21
    +0.14
    0.8%
    270
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    15
    +0.15
    0.03
    283
    +0.14
    0.02
    270
    +0.13
    0.03
    Negative Logits
    ĥ½
    -3.49
    »¿
    -3.35
    «
    -3.21
    İ
    -3.11
    ↵
    -2.99
    -2.99
    ↵↵
    -2.99
     ↵
    -2.99
    č↵
    -2.99
    ↵
    -2.99
    POSITIVE LOGITS
     experimentally
    2.19
     immunohist
    2.17
     elsewhere
    2.05
     to
    2.03
     ^[@
    1.94
     clinically
    1.92
     prospectively
    1.92
     spectrosc
    1.90
     in
    1.87
     previously
    1.84
    Activations Density 0.073%

    No Known Activations