© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 25543
    Prev
    Next
    INDEX
    Explanations

    elements related to visual 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
    11
    +0.14
    0.8%
    348
    +0.13
    0.7%
    23
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    333
    +0.14
    0.22
    49
    +0.13
    0.22
    473
    +0.10
    0.24
    Negative Logits
    blogger
    -2.13
    Animation
    -1.80
     featured
    -1.79
    lickr
    -1.79
     performer
    -1.78
     photographer
    -1.66
    widgets
    -1.65
    Illustration
    -1.62
    bows
    -1.59
    screen
    -1.59
    POSITIVE LOGITS
    ģ
    3.42
    ĥ
    3.11
    ±
    2.86
    ĺ
    2.83
    °
    2.83
    ¹
    2.76
    Ĥ
    2.68
    ĵ
    2.68
    ¢
    2.62
    Ĩ
    2.62
    Activations Density 3.795%

    No Known Activations