© 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 EvalsExportsAPI 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. 10194
    Prev
    Next
    INDEX
    Explanations

    terms related to drilling and extraction processes in the oil and gas industry

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.13
    0.7%
    182
    +0.12
    0.7%
    392
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    58
    +0.13
    0.03
    392
    +0.12
    0.04
    182
    +0.12
    0.04
    Negative Logits
    ķ
    -1.96
     vez
    -1.66
     Reader
    -1.65
     pand
    -1.65
     messenger
    -1.59
     pregnancy
    -1.54
     lamb
    -1.54
     delighted
    -1.54
     nervous
    -1.54
    Ŀ
    -1.52
    POSITIVE LOGITS
     minerals
    2.19
     drilled
    2.14
     wells
    2.08
     drilling
    2.08
    stone
    2.00
    craft
    1.95
    ship
    1.87
    ipeline
    1.81
     mining
    1.75
     excav
    1.75
    Activations Density 0.453%

    No Known Activations