© 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. 25445
    Prev
    Next
    INDEX
    Explanations

    references to tuples in programming

    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
    380
    +0.16
    1.0%
    376
    +0.15
    0.9%
    454
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    380
    +0.16
    0.01
    454
    +0.15
    0.01
    378
    +0.11
    0.01
    Negative Logits
    ---|---|---
    -1.74
     sudden
    -1.73
    rage
    -1.66
     spite
    -1.63
    ---|---
    -1.59
     him
    -1.57
     peace
    -1.54
     loud
    -1.53
     slow
    -1.51
    rocyte
    -1.51
    POSITIVE LOGITS
    esan
    1.98
    ional
    1.95
    chaft
    1.90
    ionale
    1.86
    amente
    1.85
    ioni
    1.74
    enos
    1.70
    igent
    1.69
    ior
    1.69
    endor
    1.69
    Activations Density 0.006%

    No Known Activations