© 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. 25191
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal principles and terminology

    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
    7
    +0.15
    0.8%
    444
    +0.14
    0.8%
    445
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    444
    +0.15
    0.06
    386
    +0.14
    0.05
    445
    +0.13
    0.04
    Negative Logits
     passing
    -1.68
     ‘
    -1.64
    moving
    -1.61
    ferentially
    -1.56
     narrowing
    -1.53
     proportion
    -1.49
     lowering
    -1.48
    changing
    -1.47
     \'
    -1.46
    :`
    -1.41
    POSITIVE LOGITS
    1.78
    1.72
    zilla
    1.71
    pero
    1.69
    ↵
    1.64
     etc
    1.56
    ÃŃo
    1.52
    oto
    1.48
    noreply
    1.47
    1.46
    Activations Density 0.720%

    No Known Activations