© 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. 2-MLP-SM
    11. 23690
    Prev
    Next
    INDEX
    Explanations

    instances of the term "et al." in legal contexts

    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
    97
    +0.12
    0.7%
    219
    +0.12
    0.6%
    332
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    463
    +0.12
    0.01
    249
    +0.12
    0.02
    97
    +0.11
    0.01
    Negative Logits
    ETHOD
    -1.64
    journal
    -1.59
     Reporter
    -1.50
     filed
    -1.49
     miscar
    -1.49
    ureus
    -1.48
     hereby
    -1.48
     investigative
    -1.46
     eas
    -1.45
     squash
    -1.43
    POSITIVE LOGITS
     footsteps
    1.66
    ł
    1.57
     Equation
    1.56
    Ĺ
    1.51
    ¿½
    1.48
    xygen
    1.48
    ¢
    1.48
    ĸ
    1.44
     tails
    1.42
    veis
    1.42
    Activations Density 0.195%

    No Known Activations