© 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. 9661
    Prev
    Next
    INDEX
    Explanations

    references to environmental themes or entities, specifically related to the "Green" concept

    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
    +0.17
    1.0%
    369
    +0.15
    0.9%
    43
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.17
    0.02
    59
    +0.15
    0.02
    1
    +0.15
    0.02
    Negative Logits
    quee
    -1.69
     hers
    -1.67
    ursuant
    -1.65
     succeeding
    -1.63
    urgical
    -1.60
    ctic
    -1.51
    onte
    -1.47
    umatic
    -1.45
    lique
    -1.45
    ynthesis
    -1.42
    POSITIVE LOGITS
    leaf
    2.43
    wald
    2.09
    berg
    1.96
    peace
    1.88
    back
    1.85
    grass
    1.85
    horn
    1.82
    backs
    1.79
    wall
    1.75
    bean
    1.75
    Activations Density 0.102%

    No Known Activations