© 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. 14189
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental issues and policies

    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
    156
    +0.21
    1.3%
    282
    +0.13
    0.8%
    219
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    360
    +0.21
    0.02
    418
    +0.13
    0.00
    424
    +0.12
    0.01
    Negative Logits
    Į
    -2.05
    lla
    -1.90
    ĥ½
    -1.87
    pton
    -1.75
    apest
    -1.75
    dorff
    -1.66
    ukin
    -1.65
    Ĥ¬
    -1.56
    cester
    -1.53
    pless
    -1.52
    POSITIVE LOGITS
     hazards
    1.86
    ists
    1.84
     pollution
    1.82
    ist
    1.74
     considerations
    1.74
    isation
    1.71
    ism
    1.68
     sources
    1.66
     backgrounds
    1.63
     groups
    1.60
    Activations Density 0.094%

    No Known Activations