Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27594
    Prev
    Next
    INDEX
    Explanations

    keywords related to orders and processing

    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
    113
    +0.15
    0.9%
    376
    +0.12
    0.7%
    95
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    113
    +0.15
    0.02
    460
    +0.12
    0.02
    95
    +0.11
    0.02
    Negative Logits
    ---|---
    -1.65
    thens
    -1.56
    semin
    -1.56
    rapy
    -1.56
    ))$.
    -1.55
    ---|---|---
    -1.55
    |$.
    -1.54
    ffield
    -1.54
    ktiv
    -1.51
    $.[]{
    -1.49
    POSITIVE LOGITS
    heet
    2.28
    ģ
    1.74
     mant
    1.71
    ingly
    1.69
    amente
    1.69
    hold
    1.66
    etable
    1.59
    ¢
    1.57
    ¾
    1.53
     orders
    1.47
    Activations Density 0.014%

    No Known Activations