© 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. 30228
    Prev
    Next
    INDEX
    Explanations

    mentions of food-related terms

    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
    465
    +0.11
    0.6%
    376
    +0.10
    0.6%
    276
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    465
    +0.11
    0.02
    167
    +0.10
    0.02
    200
    +0.10
    0.01
    Negative Logits
    iginally
    -1.52
    hin
    -1.52
    ubicin
    -1.51
     better
    -1.50
     resigned
    -1.49
    ி
    -1.47
    áĢ¯
    -1.45
    ']))
    -1.45
    à¯
    -1.45
    ancel
    -1.44
    POSITIVE LOGITS
    ¥
    1.71
     panels
    1.70
    campaign
    1.66
    loop
    1.61
    IJ
    1.58
    nor
    1.56
    owa
    1.55
     campaign
    1.54
    nell
    1.52
    ENTIAL
    1.52
    Activations Density 0.043%

    No Known Activations