© 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. 14337
    Prev
    Next
    INDEX
    Explanations

    words related to legal terminology and concepts

    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
    419
    +0.20
    1.2%
    332
    +0.14
    0.8%
    422
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    419
    +0.20
    0.06
    253
    +0.14
    0.06
    386
    +0.12
    0.03
    Negative Logits
    angs
    -1.79
    npmjs
    -1.51
    typeof
    -1.41
    iary
    -1.38
    illin
    -1.35
    º
    -1.33
    cdn
    -1.30
     ||
    -1.28
    ĭ
    -1.27
    rape
    -1.26
    POSITIVE LOGITS
    ership
    1.57
    ciliation
    1.43
    binant
    1.40
    velt
    1.40
    PORT
    1.36
    ologous
    1.34
     sides
    1.34
     bonds
    1.32
    ject
    1.30
     talks
    1.30
    Activations Density 0.559%

    No Known Activations