© 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. 2-MLP-SM
    11. 25272
    Prev
    Next
    INDEX
    Explanations

    references to calcium and its related biochemical processes

    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
    156
    +0.36
    2.2%
    367
    +0.12
    0.7%
    199
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.36
    0.02
    374
    +0.12
    0.01
    40
    +0.11
    0.01
    Negative Logits
    ®
    -2.71
    Ī
    -2.64
                  ↵
    -2.61
    <|outofrange|>
    -2.61
    ↵↵
    -2.61
    -2.61
    č↵
    -2.61
    -2.61
    -2.61
    ↵  ³³³
    -2.61
    POSITIVE LOGITS
     lives
    1.64
     life
    1.55
     course
    1.54
    awning
    1.54
     disposal
    1.50
    ld
    1.49
     lif
    1.48
     fit
    1.41
     objects
    1.39
    filled
    1.39
    Activations Density 0.371%

    No Known Activations