© 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. 1-RES-SM
    11. 28804
    Prev
    Next
    INDEX
    Explanations

    terms related to energy and environmental topics

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.13
    0.7%
    249
    +0.12
    0.6%
    341
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.13
    0.03
    71
    +0.12
    0.04
    249
    +0.12
    0.02
    Negative Logits
     hers
    -1.92
     adoles
    -1.77
     homosexuality
    -1.72
     gay
    -1.69
     sexuality
    -1.63
     offender
    -1.61
    ĥ½
    -1.61
     manners
    -1.61
    uffle
    -1.58
    oles
    -1.58
    POSITIVE LOGITS
    erated
    1.77
     Industries
    1.76
    Bank
    1.74
    Company
    1.73
    ICE
    1.71
    ICES
    1.71
    workers
    1.71
     Agency
    1.67
    Energy
    1.63
     Fuel
    1.60
    Activations Density 0.257%

    No Known Activations