© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 14386
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental issues and health impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/4-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.4.hook_resid_post
    Hook Layer
    4
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.16
    0.9%
    52
    +0.12
    0.7%
    78
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.16
    0.04
    360
    +0.12
    0.04
    154
    +0.10
    0.04
    Negative Logits
    ĥ½
    -3.33
    Ĥ¬
    -3.32
    Į
    -3.10
    ª
    -3.00
    İ
    -2.80
    Ŀ
    -2.79
    ķ
    -2.75
    ĩ
    -2.68
    Ī
    -2.64
    Ļ
    -2.58
    POSITIVE LOGITS
     pollution
    2.46
     hazards
    2.42
    ists
    2.34
     sustainability
    2.32
    ist
    2.29
     impacts
    2.19
     pollutants
    2.17
     sciences
    2.10
     pollut
    2.00
     concerns
    1.98
    Activations Density 0.359%

    No Known Activations