© 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. 29236
    Prev
    Next
    INDEX
    Explanations

    terms associated with food, specifically salads and salad-related ingredients

    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
    156
    +0.31
    1.8%
    232
    +0.12
    0.7%
    356
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.31
    0.03
    111
    +0.12
    0.03
    232
    +0.12
    0.02
    Negative Logits
     enjoyment
    -1.53
     directions
    -1.46
     apart
    -1.40
     heights
    -1.39
    edly
    -1.35
     fingers
    -1.34
     finger
    -1.34
    iasis
    -1.34
    ças
    -1.32
    RAF
    -1.25
    POSITIVE LOGITS
    icate
    1.60
    arial
    1.43
    dtd
    1.41
    ya
    1.39
    ocur
    1.35
    ibr
    1.33
    }}</
    1.32
    ]]
    1.32
    ome
    1.32
    à±į
    1.31
    Activations Density 0.082%

    No Known Activations