© 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. MLP Post
    9. 0-MLP-SM
    11. 30020
    Prev
    Next
    INDEX
    Explanations

    references to plant-based protein sources

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    457
    +0.15
    0.9%
    164
    +0.14
    0.8%
    43
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.15
    0.02
    457
    +0.14
    0.02
    191
    +0.12
    0.02
    Negative Logits
    OOGLE
    -1.66
    odot
    -1.64
     ')
    -1.57
     ")
    -1.57
    here
    -1.56
    obbsee
    -1.55
     slightest
    -1.52
    schem
    -1.47
    anian
    -1.45
    ients
    -1.43
    POSITIVE LOGITS
    ÅĽci
    2.28
    ÅĨ
    1.79
    works
    1.75
    cie
    1.75
    vue
    1.65
     awards
    1.65
    recht
    1.62
    ema
    1.62
    ÅĽÄĩ
    1.57
    vre
    1.56
    Activations Density 0.237%

    No Known Activations