© 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. 26691
    Prev
    Next
    INDEX
    Explanations

    mention of contracts or agreements

    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
    376
    +0.14
    0.8%
    407
    +0.11
    0.6%
    212
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    212
    +0.14
    0.03
    39
    +0.11
    0.03
    106
    +0.11
    0.03
    Negative Logits
     %>
    -1.78
     <%=
    -1.55
     </
    -1.51
     way
    -1.50
    icrobial
    -1.45
     award
    -1.44
    $.[]{
    -1.44
    Console
    -1.42
     annual
    -1.41
     Licensed
    -1.41
    POSITIVE LOGITS
     puzzles
    1.95
    stones
    1.73
    ips
    1.67
    chaft
    1.66
     than
    1.64
    bags
    1.64
    encial
    1.63
    fires
    1.62
    break
    1.57
    ious
    1.57
    Activations Density 0.139%

    No Known Activations