© 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. 26294
    Prev
    Next
    INDEX
    Explanations

    the term "appropriately" and its variations, indicating a focus on proper behavior or standards in various 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/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
    +0.19
    1.1%
    376
    +0.17
    1.0%
    455
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    455
    +0.19
    0.01
    309
    +0.17
    0.01
    404
    +0.12
    0.01
    Negative Logits
    uten
    -1.73
    ELD
    -1.70
    enson
    -1.69
    IJ
    -1.62
    ocyst
    -1.57
    ink
    -1.56
    ika
    -1.49
    Ĵ
    -1.49
    inker
    -1.48
    ake
    -1.47
    POSITIVE LOGITS
     speaking
    1.50
     alleging
    1.50
     enough
    1.44
     please
    1.42
     sized
    1.41
     titled
    1.41
     assigning
    1.40
     citing
    1.40
     shutting
    1.40
     Pence
    1.39
    Activations Density 0.115%

    No Known Activations