© 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. 4-RES-SM
    11. 11316
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental impact and 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/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
    76
    +0.13
    0.7%
    312
    +0.11
    0.6%
    466
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.13
    0.06
    32
    +0.11
    0.04
    140
    +0.11
    0.04
    Negative Logits
    ĻĤ
    -2.81
    ģ
    -1.77
    ³
    -1.71
    ¿
    -1.70
    ij
    -1.67
    ĥ
    -1.64
    Į
    -1.59
    ¤
    -1.58
    į
    -1.57
    Īĺ
    -1.56
    POSITIVE LOGITS
     than
    3.99
     fewer
    3.63
    than
    3.59
     less
    3.48
     weaker
    3.44
     richer
    3.39
     shorter
    3.38
     poorer
    3.31
     greater
    3.31
     narrower
    3.29
    Activations Density 1.348%

    No Known Activations