© 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. 26051
    Prev
    Next
    INDEX
    Explanations

    mentions of restaurants or dining establishments

    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
    +0.33
    2.0%
    184
    +0.12
    0.7%
    376
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.33
    0.03
    156
    +0.12
    0.02
    127
    +0.10
    0.02
    Negative Logits
    ĥ½
    -3.38
    IJ
    -2.80
    Ĥ
    -2.77
    ĺ
    -2.74
    Ĵ
    -2.52
    -2.49
    -2.49
    -2.49
    -2.49
    ↵
    -2.49
    POSITIVE LOGITS
    yard
    1.58
    yards
    1.57
     deserves
    1.50
    "];
    1.49
     lacks
    1.45
    entially
    1.45
    fellow
    1.44
    fors
    1.42
    break
    1.41
    itis
    1.41
    Activations Density 0.031%

    No Known Activations