© 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. 2-RES-SM
    11. 32315
    Prev
    Next
    INDEX
    Explanations

    medical terms and concepts related to gastrointestinal health and function

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    489
    +0.18
    1.0%
    17
    +0.15
    0.9%
    141
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    141
    +0.18
    0.06
    489
    +0.15
    0.03
    326
    +0.14
    0.03
    Negative Logits
     skew
    -1.89
    "|
    -1.66
     bijection
    -1.42
     appeal
    -1.38
     herself
    -1.35
     ear
    -1.34
     lane
    -1.29
     sharp
    -1.27
     ","
    -1.27
     vocals
    -1.26
    POSITIVE LOGITS
    ·
    3.13
    ĭ
    2.90
    ¸
    2.90
    Ĥ
    2.78
    į
    2.76
    ¯
    2.75
    Ħ
    2.68
    ģ
    2.66
    Ĺ
    2.52
    Ķ
    2.52
    Activations Density 1.121%

    No Known Activations