© 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. 30277
    Prev
    Next
    INDEX
    Explanations

    references to food-related gatherings or meals

    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
    66
    +0.11
    0.6%
    176
    +0.11
    0.6%
    223
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.11
    0.36
    23
    +0.11
    0.31
    494
    +0.11
    0.25
    Negative Logits
    ļ
    -2.15
    ĭ
    -2.11
    ı
    -1.88
    į
    -1.87
    £
    -1.85
    ³
    -1.76
    ivers
    -1.68
    iven
    -1.65
    §
    -1.65
    Ĵ
    -1.64
    POSITIVE LOGITS
     contrary
    1.92
     doubt
    1.80
    forth
    1.73
    encephal
    1.66
    aled
    1.64
    hered
    1.58
     disbelief
    1.55
    aside
    1.44
     mock
    1.43
     primary
    1.38
    Activations Density 3.305%

    No Known Activations