© 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. 2-MLP-SM
    11. 23115
    Prev
    Next
    INDEX
    Explanations

    references to cheese and related dairy products 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/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
    23
    +0.24
    1.3%
    311
    +0.11
    0.6%
    344
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.24
    0.04
    311
    +0.11
    0.06
    344
    +0.11
    0.07
    Negative Logits
    inux
    -1.97
    ½
    -1.94
    erna
    -1.93
    ements
    -1.71
    ución
    -1.59
    ers
    -1.55
    ī
    -1.54
    pero
    -1.54
    lez
    -1.52
    »
    -1.52
    POSITIVE LOGITS
    igated
    1.70
     ^[@
    1.67
     ')
    1.67
     initiated
    1.52
    ');
    1.52
    '),
    1.51
     findings
    1.50
     ).
    1.48
     ',
    1.48
     '</
    1.48
    Activations Density 0.562%

    No Known Activations