© 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. 29529
    Prev
    Next
    INDEX
    Explanations

    references to witnesses 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/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
    463
    +0.13
    0.7%
    492
    +0.13
    0.7%
    166
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    72
    +0.13
    0.03
    166
    +0.13
    0.02
    463
    +0.12
    0.03
    Negative Logits
    ĥ½
    -4.05
    ĻĤ
    -3.87
    Į
    -3.64
    ŀ
    -3.62
    <|outofrange|>
    -3.59
    ↵
    -3.59
    <|outofrange|>
    -3.59
    -3.59
    -3.59
    ↵
    -3.59
    POSITIVE LOGITS
     quarters
    1.91
    ships
    1.80
     areas
    1.68
    idone
    1.63
    grounds
    1.58
    cule
    1.57
    bourg
    1.57
    films
    1.57
    xico
    1.55
    ership
    1.54
    Activations Density 0.042%

    No Known Activations