© 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 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. 24763
    Prev
    Next
    INDEX
    Explanations

    CSS styles and layout properties used in web design

    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
    373
    +0.14
    0.8%
    156
    +0.14
    0.8%
    85
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.14
    0.04
    85
    +0.14
    0.03
    10
    +0.11
    0.03
    Negative Logits
    CDATA
    -1.81
    TeX
    -1.76
     editor
    -1.73
    aptic
    -1.68
     layout
    -1.59
     editors
    -1.54
    widgets
    -1.53
    transl
    -1.44
    format
    -1.43
    layout
    -1.41
    POSITIVE LOGITS
    °
    2.13
    ķ
    1.78
    tees
    1.64
    ¹
    1.64
    ees
    1.62
     Ware
    1.58
    ĵ
    1.56
    ĥ
    1.56
     creditors
    1.52
    Ī
    1.50
    Activations Density 0.272%

    No Known Activations