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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 28340
    Prev
    Next
    INDEX
    Explanations

    terms related to oil and gas production

    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
    +0.18
    1.1%
    437
    +0.11
    0.7%
    316
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    437
    +0.18
    0.03
    336
    +0.11
    0.02
    113
    +0.11
    0.02
    Negative Logits
     slightest
    -1.80
     favor
    -1.77
     favour
    -1.71
     matern
    -1.70
     maternal
    -1.67
    TRODUCTION
    -1.64
     teaching
    -1.58
     faculty
    -1.55
     vez
    -1.55
     hers
    -1.54
    POSITIVE LOGITS
    skins
    2.19
    cloth
    2.10
    skin
    2.06
    stone
    2.06
    gas
    1.96
    chip
    1.91
    soluble
    1.89
    makers
    1.88
    borne
    1.84
    beam
    1.83
    Activations Density 0.129%

    No Known Activations