© 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. 1-RES-SM
    11. 23901
    Prev
    Next
    INDEX
    Explanations

    terms related to the frequency and impact of health-related issues or conditions

    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/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
    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.17
    1.0%
    118
    +0.13
    0.7%
    308
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    241
    +0.17
    0.01
    156
    +0.13
    0.01
    215
    +0.12
    0.01
    Negative Logits
    Īĺ
    -2.42
    ĥ½
    -2.40
    ¼
    -2.38
    ½
    -2.33
    ¿½
    -2.17
    İ
    -2.14
    ¹
    -2.08
    ±
    -2.07
    ®
    -2.05
    ĸ´
    -2.04
    POSITIVE LOGITS
     estimates
    1.79
     estimate
    1.73
     rates
    1.71
     estimated
    1.69
     proportions
    1.65
    arial
    1.64
     area
    1.64
    orted
    1.61
    iest
    1.58
     ratio
    1.58
    Activations Density 0.050%

    No Known Activations