© 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. 2-RES-SM
    11. 27304
    Prev
    Next
    INDEX
    Explanations

    terms related to energy and environmental sustainability

    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
    111
    +0.14
    0.8%
    122
    +0.13
    0.7%
    231
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    114
    +0.14
    0.08
    478
    +0.13
    0.00
    154
    +0.12
    0.07
    Negative Logits
    (_
    -1.66
    ($_
    -1.60
    hores
    -1.57
    =$(
    -1.53
    py
    -1.48
     (_
    -1.47
    async
    -1.42
    ano
    -1.42
    =$
    -1.42
    apple
    -1.41
    POSITIVE LOGITS
    ¿½
    3.24
    Ļ
    3.01
    ª
    2.92
    ³
    2.90
    ĵ
    2.90
    «
    2.88
    ŀ
    2.85
    »
    2.82
    ¬
    2.71
    »¿
    2.71
    Activations Density 1.822%

    No Known Activations