© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 31059
    Prev
    Next
    INDEX
    Explanations

    the term "Green" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    369
    +0.21
    1.2%
    59
    +0.13
    0.8%
    376
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.21
    0.02
    43
    +0.13
    0.02
    134
    +0.13
    0.02
    Negative Logits
     its
    -1.97
    ĥ½
    -1.87
    ı
    -1.79
    Ń
    -1.78
    ĭ
    -1.76
    ĨĴ
    -1.72
    ters
    -1.69
    Ļª
    -1.68
    ties
    -1.66
    ĩ
    -1.66
    POSITIVE LOGITS
    leaf
    2.25
    grass
    2.12
    wich
    1.89
    fruit
    1.87
    face
    1.80
    houses
    1.78
    wald
    1.74
    foods
    1.73
    castle
    1.70
    wall
    1.65
    Activations Density 0.086%

    No Known Activations