© 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. 25666
    Prev
    Next
    INDEX
    Explanations

    terms related to phosphorylation and signaling pathways in biological 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/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
    156
    +0.18
    1.1%
    466
    +0.12
    0.7%
    511
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    293
    +0.18
    0.01
    317
    +0.12
    0.01
    511
    +0.10
    0.01
    Negative Logits
    ĥ½
    -1.83
    ---|---
    -1.57
    ½
    -1.54
     reconsider
    -1.52
    ķ
    -1.51
    rely
    -1.50
    ¼
    -1.49
     Publ
    -1.49
    |$.
    -1.48
    llll
    -1.48
    POSITIVE LOGITS
     led
    1.68
    erve
    1.66
     renders
    1.65
    ist
    1.59
    imal
    1.55
     era
    1.53
     vault
    1.53
     event
    1.52
     tolerance
    1.52
     apparatus
    1.52
    Activations Density 0.011%

    No Known Activations