© 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. 0-MLP-SM
    11. 26794
    Prev
    Next
    INDEX
    Explanations

    the word "as" used in various contexts

    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
    228
    +0.14
    0.8%
    374
    +0.12
    0.6%
    182
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    424
    +0.14
    0.17
    502
    +0.12
    0.15
    479
    +0.10
    0.15
    Negative Logits
     apart
    -1.78
     together
    -1.63
    nier
    -1.61
    mented
    -1.51
     equivalent
    -1.49
     variants
    -1.49
     if
    -1.47
    icker
    -1.47
     into
    -1.46
    olved
    -1.44
    POSITIVE LOGITS
    Ľ
    1.72
    blogger
    1.68
    usiness
    1.56
    zerba
    1.52
    usterity
    1.49
     SEO
    1.48
    ļ
    1.46
    blast
    1.45
    ŀ
    1.45
    oddsidemargin
    1.45
    Activations Density 0.326%

    No Known Activations