© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 25474
    Prev
    Next
    INDEX
    Explanations

    concepts related to weight management and obesity

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    23
    +0.20
    1.1%
    156
    +0.17
    1.0%
    205
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.20
    0.01
    23
    +0.17
    0.01
    277
    +0.12
    0.03
    Negative Logits
    Ł
    -2.88
    »¿
    -2.71
    º
    -2.67
    Ĵ
    -2.62
    ĻĤ
    -2.56
    ĸ
    -2.52
    Ľ
    -2.51
    Ĭ
    -2.50
    ļ
    -2.48
    -2.45
    POSITIVE LOGITS
     Congress
    1.70
     '+
    1.59
    ostatin
    1.47
     Parliament
    1.43
     Whats
    1.42
    usp
    1.38
    edin
    1.33
    onas
    1.33
     FDR
    1.31
     peaceful
    1.31
    Activations Density 0.282%

    No Known Activations