© 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 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. 28519
    Prev
    Next
    INDEX
    Explanations

    the context of the term "Convert."

    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%
    89
    +0.13
    0.7%
    5
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    321
    +0.14
    0.02
    109
    +0.13
    0.02
    239
    +0.12
    0.01
    Negative Logits
     brow
    -1.66
    ald
    -1.56
    return
    -1.54
    kt
    -1.46
    ren
    -1.45
    Bye
    -1.44
     crossed
    -1.40
    ATE
    -1.37
    THAT
    -1.35
    exists
    -1.35
    POSITIVE LOGITS
    pile
    1.98
    \]](
    1.84
    ibles
    1.77
    chaft
    1.74
    ÃŃvel
    1.73
    ipore
    1.72
    aceut
    1.72
    naire
    1.70
    imab
    1.68
     outlet
    1.62
    Activations Density 1.290%

    No Known Activations