© 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. 32305
    Prev
    Next
    INDEX
    Explanations

    references to human rights issues and related social injustices

    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
    +0.21
    1.3%
    186
    +0.18
    1.1%
    326
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    276
    +0.21
    0.06
    330
    +0.18
    0.10
    419
    +0.14
    0.09
    Negative Logits
    "}](#
    -1.63
     onCreate
    -1.52
    msgstr
    -1.42
    ={
    -1.41
    enium
    -1.40
    chitz
    -1.35
    illin
    -1.34
    oscope
    -1.28
    :{
    -1.27
    afx
    -1.26
    POSITIVE LOGITS
    ¾
    2.03
    «
    1.78
     Depression
    1.60
    ĥ½
    1.57
    µ
    1.55
    opter
    1.50
     dorm
    1.49
    Ĥ¬
    1.47
     community
    1.44
     tragedy
    1.42
    Activations Density 8.379%

    No Known Activations