© 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. 29564
    Prev
    Next
    INDEX
    Explanations

    references to luxury and high-end experiences

    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
    +0.22
    1.3%
    126
    +0.11
    0.7%
    241
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    126
    +0.22
    0.01
    311
    +0.11
    0.01
    231
    +0.11
    0.01
    Negative Logits
     href
    -1.47
    еÑĤÑģÑı
    -1.43
    eps
    -1.39
    rica
    -1.39
    estamp
    -1.38
    erral
    -1.38
    ../../
    -1.35
    аÑģ
    -1.33
    ëĬ
    -1.32
    ÑĢоÑģ
    -1.31
    POSITIVE LOGITS
    "}](#
    2.16
    ously
    2.06
    ively
    1.89
    istically
    1.87
    ibly
    1.57
    ioned
    1.54
    osa
    1.53
    ious
    1.48
    naire
    1.43
    ently
    1.42
    Activations Density 0.244%

    No Known Activations